feat(skills): ship use-ig (Praxis-MCP read variant) at login#60
Merged
Conversation
Add a second binary-embedded tree skill, `use-ig`, that praxis installs
during `praxis login`. It is the Praxis-MCP READ variant of ig's native
use-ig skill: the graph query mental-model (catalog / members /
interface-nodes / calls|deploys_as|provisions edges) and the worked
examples (FE->BE trace, blast-radius/impact, where-does-X-live) are
preserved, but the whole invocation surface is swapped to the server-side
`praxis mcp ig` tools (ig_list_catalogs / ig_explain / ig_impact /
ig_query), so the host needs no local `ig` binary, no synced tree, and no
cloud secrets. Same bare name as ig's native skill — only one is ever
installed at a time (ig ships its native copy only when praxis is absent).
Wiring:
- Generalize the tree-skill embed: rename onboardingTreeFiles ->
treeSkillFiles, embed both embedded/praxis-onboarding and
embedded/use-ig, and drive treeSkills() off a treeSkillNames slice.
MetaSkillNames()/IsMetaSkill() therefore pick up use-ig with no further
change, so login installs it and profile switches preserve it.
Tests (TDD, RED->GREEN):
- MetaSkillNames() includes "use-ig" (and stays sorted).
- IsMetaSkill("use-ig") is true (survives profile switch).
- treeSkillFS("use-ig") SKILL.md has `name: use-ig`, invokes reads via
`praxis mcp ig`, and carries no local-`ig` read command surface
(guards this is the MCP variant, not the native one).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
WalkthroughThe PR embeds multiple tree skills, adds the ChangesEmbedded use-ig skill
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
internal/skillinstall/embedded/use-ig/SKILL.md (1)
32-32: 📐 Maintainability & Code Quality | 🔵 Trivial | ⚡ Quick winAdd language identifiers to the fenced blocks.
markdownlint-cli2reports MD040 for these four fences. Usetextfor the graph diagram andconsoleortextfor command examples.Also applies to: 45-45, 85-85, 148-148
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@internal/skillinstall/embedded/use-ig/SKILL.md` at line 32, Add explicit language identifiers to all four fenced code blocks in SKILL.md to satisfy MD040: use text for the graph diagram and console or text for the command examples. Update only the affected fences, including those around the referenced sections.Source: Linters/SAST tools
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@internal/skillinstall/embedded_test.go`:
- Around line 63-71: Update the embedded skill validation test around the
existing praxis mcp ig assertions to use a table-driven list containing
ig_list_catalogs, ig_explain, ig_impact, and ig_query, and explicitly assert
each command appears in body. Retain the existing check preventing the native
`ig query` command surface.
In `@internal/skillinstall/embedded/use-ig/SKILL.md`:
- Around line 30-37: Update the catalog/target requirement guidance around
ig_list_catalogs to explicitly identify it as the argument-free discovery
exception, and state that only the remaining three tools require catalog and
target arguments. Keep the existing discovery command and subsequent
catalog-selection instructions unchanged.
---
Nitpick comments:
In `@internal/skillinstall/embedded/use-ig/SKILL.md`:
- Line 32: Add explicit language identifiers to all four fenced code blocks in
SKILL.md to satisfy MD040: use text for the graph diagram and console or text
for the command examples. Update only the affected fences, including those
around the referenced sections.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 2807f494-c870-41c0-ada3-31bf8b8c8dae
📒 Files selected for processing (3)
internal/skillinstall/embedded.gointernal/skillinstall/embedded/use-ig/SKILL.mdinternal/skillinstall/embedded_test.go
Comment on lines
+63
to
+71
| // Reads must route through the Praxis MCP. | ||
| if !strings.Contains(body, "praxis mcp ig") { | ||
| t.Errorf("use-ig SKILL.md must invoke reads via `praxis mcp ig` (MCP variant)") | ||
| } | ||
| // It must NOT carry the native local-`ig` read command surface. The | ||
| // backticked `ig query` is the tell of the local-ig variant; this MCP | ||
| // copy uses `praxis mcp ig ig_query` instead. | ||
| if strings.Contains(body, "`ig query`") { | ||
| t.Errorf("use-ig SKILL.md contains local-ig read command `ig query`; this must be the `praxis mcp ig` variant") |
There was a problem hiding this comment.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
Assert every required MCP tool explicitly.
Checking only for the generic praxis mcp ig prefix would still pass if one of the required tools were removed from the skill. Assert all four commands: ig_list_catalogs, ig_explain, ig_impact, and ig_query.
As per coding guidelines, use a table-driven test for the required tool list.
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@internal/skillinstall/embedded_test.go` around lines 63 - 71, Update the
embedded skill validation test around the existing praxis mcp ig assertions to
use a table-driven list containing ig_list_catalogs, ig_explain, ig_impact, and
ig_query, and explicitly assert each command appears in body. Retain the
existing check preventing the native `ig query` command surface.
Source: Coding guidelines
…kill
The ig read verbs address a node per member (`ig <verb> <member> <target>`), and
the server-side MCP now requires `--arg member=<m>`. The skill was written for a
single `--arg target=<node>`, so an agent following it would hit "member is
required" on every read call.
Teach `member` as a lens into the graph of graphs:
* member=catalog -> interface/connection layer (service:/route:/graph: nodes +
cross-repo calls/deploys_as/provisions edges) — where "how repos connect" lives
* member=<repo> -> that repo's code graph
* member=infra -> the Facets infra graph
Updates the command surface, list-catalogs (now returns members), recipes, the
worked example, and adds a "wrong member = no node" gotcha. Mirrors the
already-correct 2-positional model in infragraphify's native use-ig skill.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@internal/skillinstall/embedded/use-ig/SKILL.md`:
- Around line 119-147: Update every ig_explain and ig_query invocation in the
documented recipes to include the required selected catalog argument in the form
--arg catalog=<c>. Preserve each command’s existing member and target arguments
while applying this consistently across all examples.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 6f4877b4-019a-4b7f-9b82-d299d6ee8615
📒 Files selected for processing (1)
internal/skillinstall/embedded/use-ig/SKILL.md
…_path, ig_catalog
The server-side ig MCP grew to full raw-ig read parity (agent-factory), so teach
the six tools instead of four:
* ig_query now takes FREE TEXT via `--arg query="..."` (was a node `target`),
has NO depth (ig hardcodes query depth), and takes `--arg relation=` /
`--arg context=` edge filters + `--arg budget=`.
* ig_impact gains the same relation/context filters (+ real depth).
* new ig_catalog (`--arg catalog=<c>`) — the topology map; START HERE for
"how do these connect".
* new ig_path (`--arg from_node=<a> --arg to_node=<b>`) — shortest path.
Updates the command surface, the boundary line (four → six), and the recipes
(connect-map via ig_catalog, A→B via ig_path, free-text query=).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@internal/skillinstall/embedded/use-ig/SKILL.md`:
- Line 103: Update the fenced code block in SKILL.md to specify the shell
language by changing its opening fence to ```sh, while preserving the block’s
existing shell commands and closing fence.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: b8e3b5c8-ae09-49b5-8905-052c39687741
📒 Files selected for processing (1)
internal/skillinstall/embedded/use-ig/SKILL.md
| `ig_list_catalogs`/`ig_catalog`, `--arg member=<m>` (the lens — see above). | ||
| Output is **token-budgeted TEXT** written for an LLM to read. | ||
|
|
||
| ``` |
There was a problem hiding this comment.
📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win
Specify the fenced block language.
Markdownlint reports MD040 here. Since the block contains shell commands, use ```sh instead of an untyped fence.
Proposed fix
-```
+```sh🧰 Tools
🪛 markdownlint-cli2 (0.23.0)
[warning] 103-103: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🪛 SkillSpector (2.3.11)
[warning] 66: [MP2] Context Window Stuffing: Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.
Remediation: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
(Memory Poisoning (MP2))
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@internal/skillinstall/embedded/use-ig/SKILL.md` at line 103, Update the
fenced code block in SKILL.md to specify the shell language by changing its
opening fence to ```sh, while preserving the block’s existing shell commands and
closing fence.
Source: Linters/SAST tools
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Ships
use-igas a binary-embedded tree meta-skill, installed atpraxis login.This is the Praxis-MCP read variant of ig's use-ig skill: catalog reads run
server-side via
praxis mcp ig(ig_impact/ig_query/ig_explain/ig_list_catalogs), so the host needs noigbinary for reads. Only setup +CI still need
ig+graphifylocally.Counterpart to infragraphify#40:
ig skills installnow ships the native(local-ig) use-ig only when praxis is absent; when praxis is present, it installs
this MCP copy. Same skill name (
use-ig) — exactly one exists at a time.Server side already landed in agent-factory (the
iggateway MCP:praxis mcp ig …).Changes
internal/skillinstall/embedded/use-ig/SKILL.md— MCP-route skill: graphmental-model + gotchas + recipes carried over from the canonical native skill,
invocation surface swapped to
praxis mcp ig ig_* --arg catalog= --arg target=.No local
ig/$IG_HOME/praxis ig syncin the read path.internal/skillinstall/embedded.go— embed both trees; generalizetreeSkills()over a
treeSkillNamesslice.MetaSkillNames/IsMetaSkill/login-install/profile-switch preservation pick up
use-igwith no further change.Testing (TDD)
internal/skillinstall/embedded_test.go+3:MetaSkillNamesincludesuse-ig(sorted),
IsMetaSkill("use-ig")preserved, and an MCP-variant guard (SKILL.mdhas
name: use-ig+praxis mcp ig, and NOT the local-igig querycommand).go build,go vet,gofmt,go test ./...all clean/green.Sequencing
Pairs with infragraphify#40; both gate on agent-factory's
praxis mcp igbeingdeployed so the skill's commands actually answer.
🤖 Generated with Claude Code
Summary by CodeRabbit
use-igskill for querying prebuilt catalogs and exploring service relationships (including frontend-to-backend routing and impact).use-igguide covering the catalog model, availableig_*tools, common workflows, and practical caveats.use-igstays correctly recognized across profile switches and routes throughpraxis mcp ig(not the native localigread flow).