Skip to content

Commit 2eb1935

Browse files
romgenieromgenie
committed
Add ClawHub publish readiness checks
1 parent 9caa7d5 commit 2eb1935

4 files changed

Lines changed: 341 additions & 137 deletions

File tree

‎.clawhubignore‎

Lines changed: 39 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,39 @@
1+
# ClawHub accepts text-based skill bundles. Keep generated/binary assets in GitHub only.
2+
*.png
3+
*.jpg
4+
*.jpeg
5+
*.gif
6+
*.ico
7+
*.pdf
8+
*.docx
9+
*.ipynb
10+
*.ttf
11+
*.otf
12+
*.woff
13+
*.woff2
14+
15+
preview/
16+
output/
17+
18+
__pycache__/
19+
*.py[cod]
20+
*$py.class
21+
.mypy_cache/
22+
.pytest_cache/
23+
.ruff_cache/
24+
25+
.venv/
26+
venv/
27+
env/
28+
ENV/
29+
30+
.env
31+
.env.*
32+
!.env.example
33+
secrets.json
34+
*_secret.ini
35+
*_local.ini
36+
*.tmp
37+
.DS_Store
38+
Thumbs.db
39+
desktop.ini

‎CLAW_HUB_PUBLISHING.md‎

Lines changed: 55 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,55 @@
1+
# ClawHub Publishing
2+
3+
This repository is prepared for ClawHub publishing as a text-based OpenClaw skill bundle.
4+
5+
## Included In ClawHub
6+
7+
The ClawHub bundle is intended to include text-based skill material only:
8+
9+
- `SKILL.md`, `README.md`, `QUALITY.md`, and this file
10+
- `agents/openai.yaml`
11+
- `pyproject.toml`
12+
- `.github/workflows/quality.yml`
13+
- `scripts/*.py`
14+
- `references/` text files, schemas, catalogs, and examples
15+
- `examples/` text inputs such as `.ini` files or README placeholders
16+
- `assets/diagrams/*.mmd`
17+
- config examples and templates where they are text-based
18+
19+
## Excluded From ClawHub
20+
21+
`.clawhubignore` excludes binary and generated assets from the publish candidate, including PDFs, PNG previews, DOCX files, fonts, logos, `preview/`, `output/`, caches, virtual environments, local env files, and temporary files.
22+
23+
Those files remain part of the GitHub repository for brand presentation, examples, local demos, and generated artifact previews. They are not part of the ClawHub text bundle.
24+
25+
## License And Brand Boundary
26+
27+
ClawHub publishes skills under MIT-0. The text/code bundle can be used under ClawHub's publishing terms, but CompleteTech LLC names, logos, seals, and other brand assets remain reserved. Publishing this text bundle does not grant a trademark or brand-asset license and does not relicense excluded binary brand assets.
28+
29+
## Runtime Dependencies
30+
31+
Runtime requirements are declared in `SKILL.md` under `metadata.openclaw`.
32+
33+
- All Python-backed skills require `python3`.
34+
- PDF/generator skills declare `reportlab` where PDF rendering is used.
35+
- The contract skill declares `jinja2`.
36+
- `pyyaml` is declared so the included quality/audit validator can parse YAML metadata.
37+
- Optional PNG preview dependencies such as `pypdfium2` and `pillow` are GitHub/local-demo conveniences, not required for the ClawHub core workflow unless a user intentionally runs PNG preview generation.
38+
39+
## Local Readiness Check
40+
41+
Run before publishing:
42+
43+
```bash
44+
python3 scripts/validate_quality.py
45+
```
46+
47+
The validator checks lint, Python compilation, structured-file parsing, Mermaid rendering, smoke tests, Pyright where configured, and ClawHub bundle readiness. It does not publish to ClawHub.
48+
49+
## Publishing
50+
51+
Do not publish automatically. Use the ClawHub CLI only after explicit approval and an authenticated owner context, for example:
52+
53+
```bash
54+
clawhub skill publish . --owner <owner> --version <semver>
55+
```

‎SKILL.md‎

Lines changed: 115 additions & 110 deletions
Original file line numberDiff line numberDiff line change
@@ -1,110 +1,115 @@
1-
---
2-
name: agentic-delivery-skill
3-
description: >-
4-
Create CompleteTech LLC delivery execution artifacts for approved agentic development engagements, including kickoff agendas, access checklists, project plans, milestone trackers, status updates, decision logs, risk/issue logs, change request intake, prototype review, evaluation reports, acceptance packets, launch readiness, monitoring, support, handoff, runbooks, quickstarts, closeout, post-launch review, and escalation procedures. Use after proposal/SOW or contract approval when Codex needs to run bounded agentic workflow delivery cleanly.
5-
version: 1.0.0
6-
metadata:
7-
openclaw:
8-
skillKey: agentic-delivery-skill
9-
homepage: https://github.com/CompleteTech-LLC/agentic-delivery-skill
10-
requires:
11-
bins:
12-
- python3
13-
---
14-
15-
# Agentic Delivery Skill
16-
17-
## Purpose
18-
19-
Create delivery execution artifacts for CompleteTech LLC agentic development engagements after a proposal/SOW or contract is approved.
20-
21-
## System Boundary
22-
23-
This skill owns execution after commercial approval: kickoff, project control, evaluation, launch preparation, handoff, and support artifacts. Use `agentic-proposal-skill` for unapproved commercial scope, `agentic-contract-skill` for legal agreement artifacts, `agentic-security-review-skill` for security or production-readiness review, `agentic-invoice-skill` for billing, `agentic-customer-success-skill` for relationship health and renewal, and `agentic-case-study-skill` only after outcomes are verified and approved for proof.
24-
25-
## Core Workflow
26-
27-
1. Identify the delivery need: kickoff, access, planning, status, decisions, risk/issue, change request, prototype review, evaluation, acceptance, launch, monitoring, support, handoff, closeout, or escalation.
28-
2. Gather verified facts: approved scope, workflow, owners, timeline, milestones, systems, approval gates, evaluation examples, risks, dependencies, support expectations, and acceptance criteria.
29-
3. Use `references/use-case-decision-table.md` to choose the right delivery artifact.
30-
4. Use `references/delivery-positioning.md` for CompleteTech LLC delivery framing and guardrails.
31-
5. Use `references/delivery-catalog.md` for the near-exhaustive delivery artifact library.
32-
6. Keep delivery practical and bounded. Do not fabricate client facts, approvals, test results, metrics, regulated-use assurances, legal claims, or production readiness.
33-
34-
## Artifact Selection Guide
35-
36-
- First meeting after signature: use `kickoff-agenda`.
37-
- Need client systems/docs/API access: use `client-access-checklist`.
38-
- Need execution structure: use `project-plan`.
39-
- Tracking milestone progress: use `milestone-tracker`.
40-
- Regular client update: use `weekly-status-update`.
41-
- Capturing decisions: use `decision-log`.
42-
- Capturing risks or active issues: use `risk-and-issue-log`.
43-
- Scope change request: use `change-request-intake`.
44-
- Blocking prerequisites: use `dependency-tracker`.
45-
- Communication cadence: use `stakeholder-communication-plan`.
46-
- Prototype review: use `prototype-review-checklist`.
47-
- Evaluation run: use `evaluation-run-report`.
48-
- Test summary: use `test-results-summary`.
49-
- Formal acceptance: use `acceptance-review-packet`.
50-
- Launch preparation: use `launch-readiness-checklist`.
51-
- Observability requirements: use `monitoring-plan`.
52-
- Post-handoff help: use `support-plan`.
53-
- Handoff preparation: use `handoff-checklist`.
54-
- Admin/operator documentation: use `administrator-runbook`.
55-
- Reviewer or user training: use `user-reviewer-quickstart`.
56-
- After launch: use `post-launch-review`.
57-
- Retrospective: use `lessons-learned`.
58-
- Project close: use `closeout-summary`.
59-
- Incoming support request: use `support-ticket-intake`.
60-
- Escalation path: use `escalation-procedure`.
61-
- Deployment-specific rollout: use `deployment-runbook`.
62-
- Acceptance defects: use `defect-remediation-plan`.
63-
- Client training session: use `training-session-plan`.
64-
65-
When several artifacts fit, choose the one closest to the operational event. Do not mark launch-ready, accepted, or complete unless the verified evidence supports it.
66-
67-
## Quality Rules
68-
69-
- Execute the approved scope; route new scope into change request intake.
70-
- Protect human approval gates for external communications, production changes, purchases, data export, and material business decisions.
71-
- Track decisions, risks, issues, dependencies, and acceptance evidence explicitly.
72-
- Verify evaluation examples before acceptance.
73-
- Document logs, monitoring, runbooks, quickstarts, support, and handoff.
74-
- Use `TBD` or open questions for unknowns.
75-
76-
## Resource Guide
77-
78-
- `references/delivery-positioning.md`: load for CompleteTech LLC delivery language and boundaries.
79-
- `references/use-case-decision-table.md`: load when choosing a delivery artifact.
80-
- `references/delivery-lifecycle.md`: load for flow from kickoff through support and closeout.
81-
- `references/delivery-catalog.md`: load for the near-exhaustive delivery template library.
82-
- `references/template-index.json`: machine-readable template metadata used by the renderer.
83-
- `scripts/render_delivery.py`: list delivery artifacts or render a draft with placeholders.
84-
85-
## Renderer
86-
87-
```bash
88-
python3 scripts/render_delivery.py --list
89-
python3 scripts/render_delivery.py --stage status --list
90-
python3 scripts/render_delivery.py --template kickoff-agenda --var client_name=Acme --var workflow="support triage"
91-
```
92-
93-
Rendered artifacts are drafts. Replace placeholders with verified project facts before sending or storing them.
94-
95-
## Rendering to a Branded PDF
96-
97-
Artifacts from this skill are delivered as branded CompleteTech LLC **PDF** documents, not raw Markdown. The renderer emits the PDF (and prints the Markdown) in **one command**, using the same reportlab branding engine as the contract skill:
98-
99-
```bash
100-
pip install -r requirements.txt
101-
python3 scripts/render_delivery.py --template launch-readiness-checklist \
102-
--out artifact.pdf --png artifact.png \
103-
--title "Launch Readiness Checklist" --doc-type "DELIVERY ARTIFACT" \
104-
--subtitle "Northwind Trading Co. — Support Email Triage Agent (Pilot)" --meta "DOCUMENT NO.=DEL-2026-0233" --meta "DATE=2026-06-12" \
105-
--var client_name="Client Name" --var workflow="support triage"
106-
```
107-
108-
- `--no-pdf` emits Markdown only (the original behavior); `--no-cover` drops the cover page.
109-
- Already drafted the Markdown yourself? Render it directly: `python3 scripts/render_pdf.py --markdown artifact.md --out artifact.pdf --logo assets/logo.png --title "..."`.
110-
- The PDF supports a Markdown subset: `#`/`##`/`###` headings, paragraphs, `-` bullets, tables, `>` callouts, `**bold**`, and `[PAGE_BREAK]`. PDF requires `reportlab`; the optional `--png` preview requires `pypdfium2` and `pillow`. See `assets/examples/` for a rendered example.
1+
---
2+
name: agentic-delivery-skill
3+
description: >-
4+
Create CompleteTech LLC delivery execution artifacts for approved agentic development engagements, including kickoff agendas, access checklists, project plans, milestone trackers, status updates, decision logs, risk/issue logs, change request intake, prototype review, evaluation reports, acceptance packets, launch readiness, monitoring, support, handoff, runbooks, quickstarts, closeout, post-launch review, and escalation procedures. Use after proposal/SOW or contract approval when Codex needs to run bounded agentic workflow delivery cleanly.
5+
version: 1.0.0
6+
metadata:
7+
openclaw:
8+
skillKey: agentic-delivery-skill
9+
homepage: https://github.com/CompleteTech-LLC/agentic-delivery-skill
10+
requires:
11+
bins:
12+
- python3
13+
install:
14+
- kind: uv
15+
package: reportlab>=4.0
16+
- kind: uv
17+
package: pyyaml>=6.0
18+
---
19+
20+
# Agentic Delivery Skill
21+
22+
## Purpose
23+
24+
Create delivery execution artifacts for CompleteTech LLC agentic development engagements after a proposal/SOW or contract is approved.
25+
26+
## System Boundary
27+
28+
This skill owns execution after commercial approval: kickoff, project control, evaluation, launch preparation, handoff, and support artifacts. Use `agentic-proposal-skill` for unapproved commercial scope, `agentic-contract-skill` for legal agreement artifacts, `agentic-security-review-skill` for security or production-readiness review, `agentic-invoice-skill` for billing, `agentic-customer-success-skill` for relationship health and renewal, and `agentic-case-study-skill` only after outcomes are verified and approved for proof.
29+
30+
## Core Workflow
31+
32+
1. Identify the delivery need: kickoff, access, planning, status, decisions, risk/issue, change request, prototype review, evaluation, acceptance, launch, monitoring, support, handoff, closeout, or escalation.
33+
2. Gather verified facts: approved scope, workflow, owners, timeline, milestones, systems, approval gates, evaluation examples, risks, dependencies, support expectations, and acceptance criteria.
34+
3. Use `references/use-case-decision-table.md` to choose the right delivery artifact.
35+
4. Use `references/delivery-positioning.md` for CompleteTech LLC delivery framing and guardrails.
36+
5. Use `references/delivery-catalog.md` for the near-exhaustive delivery artifact library.
37+
6. Keep delivery practical and bounded. Do not fabricate client facts, approvals, test results, metrics, regulated-use assurances, legal claims, or production readiness.
38+
39+
## Artifact Selection Guide
40+
41+
- First meeting after signature: use `kickoff-agenda`.
42+
- Need client systems/docs/API access: use `client-access-checklist`.
43+
- Need execution structure: use `project-plan`.
44+
- Tracking milestone progress: use `milestone-tracker`.
45+
- Regular client update: use `weekly-status-update`.
46+
- Capturing decisions: use `decision-log`.
47+
- Capturing risks or active issues: use `risk-and-issue-log`.
48+
- Scope change request: use `change-request-intake`.
49+
- Blocking prerequisites: use `dependency-tracker`.
50+
- Communication cadence: use `stakeholder-communication-plan`.
51+
- Prototype review: use `prototype-review-checklist`.
52+
- Evaluation run: use `evaluation-run-report`.
53+
- Test summary: use `test-results-summary`.
54+
- Formal acceptance: use `acceptance-review-packet`.
55+
- Launch preparation: use `launch-readiness-checklist`.
56+
- Observability requirements: use `monitoring-plan`.
57+
- Post-handoff help: use `support-plan`.
58+
- Handoff preparation: use `handoff-checklist`.
59+
- Admin/operator documentation: use `administrator-runbook`.
60+
- Reviewer or user training: use `user-reviewer-quickstart`.
61+
- After launch: use `post-launch-review`.
62+
- Retrospective: use `lessons-learned`.
63+
- Project close: use `closeout-summary`.
64+
- Incoming support request: use `support-ticket-intake`.
65+
- Escalation path: use `escalation-procedure`.
66+
- Deployment-specific rollout: use `deployment-runbook`.
67+
- Acceptance defects: use `defect-remediation-plan`.
68+
- Client training session: use `training-session-plan`.
69+
70+
When several artifacts fit, choose the one closest to the operational event. Do not mark launch-ready, accepted, or complete unless the verified evidence supports it.
71+
72+
## Quality Rules
73+
74+
- Execute the approved scope; route new scope into change request intake.
75+
- Protect human approval gates for external communications, production changes, purchases, data export, and material business decisions.
76+
- Track decisions, risks, issues, dependencies, and acceptance evidence explicitly.
77+
- Verify evaluation examples before acceptance.
78+
- Document logs, monitoring, runbooks, quickstarts, support, and handoff.
79+
- Use `TBD` or open questions for unknowns.
80+
81+
## Resource Guide
82+
83+
- `references/delivery-positioning.md`: load for CompleteTech LLC delivery language and boundaries.
84+
- `references/use-case-decision-table.md`: load when choosing a delivery artifact.
85+
- `references/delivery-lifecycle.md`: load for flow from kickoff through support and closeout.
86+
- `references/delivery-catalog.md`: load for the near-exhaustive delivery template library.
87+
- `references/template-index.json`: machine-readable template metadata used by the renderer.
88+
- `scripts/render_delivery.py`: list delivery artifacts or render a draft with placeholders.
89+
90+
## Renderer
91+
92+
```bash
93+
python3 scripts/render_delivery.py --list
94+
python3 scripts/render_delivery.py --stage status --list
95+
python3 scripts/render_delivery.py --template kickoff-agenda --var client_name=Acme --var workflow="support triage"
96+
```
97+
98+
Rendered artifacts are drafts. Replace placeholders with verified project facts before sending or storing them.
99+
100+
## Rendering to a Branded PDF
101+
102+
Artifacts from this skill are delivered as branded CompleteTech LLC **PDF** documents, not raw Markdown. The renderer emits the PDF (and prints the Markdown) in **one command**, using the same reportlab branding engine as the contract skill:
103+
104+
```bash
105+
pip install -r requirements.txt
106+
python3 scripts/render_delivery.py --template launch-readiness-checklist \
107+
--out artifact.pdf --png artifact.png \
108+
--title "Launch Readiness Checklist" --doc-type "DELIVERY ARTIFACT" \
109+
--subtitle "Northwind Trading Co. — Support Email Triage Agent (Pilot)" --meta "DOCUMENT NO.=DEL-2026-0233" --meta "DATE=2026-06-12" \
110+
--var client_name="Client Name" --var workflow="support triage"
111+
```
112+
113+
- `--no-pdf` emits Markdown only (the original behavior); `--no-cover` drops the cover page.
114+
- Already drafted the Markdown yourself? Render it directly: `python3 scripts/render_pdf.py --markdown artifact.md --out artifact.pdf --logo assets/logo.png --title "..."`.
115+
- The PDF supports a Markdown subset: `#`/`##`/`###` headings, paragraphs, `-` bullets, tables, `>` callouts, `**bold**`, and `[PAGE_BREAK]`. PDF requires `reportlab`; the optional `--png` preview requires `pypdfium2` and `pillow`. See `assets/examples/` for a rendered example.

0 commit comments

Comments
 (0)