You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: .github/agents/agentic-workflows.md
+46-18Lines changed: 46 additions & 18 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,6 @@
1
1
---
2
-
description: GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing
2
+
name: Agentic Workflows
3
+
description: GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.
3
4
disable-model-invocation: true
4
5
---
5
6
@@ -13,13 +14,16 @@ This is a **dispatcher agent** that routes your request to the appropriate speci
13
14
14
15
-**Creating new workflows**: Routes to `create` prompt
15
16
-**Updating existing workflows**: Routes to `update` prompt
16
-
-**Debugging workflows**: Routes to `debug` prompt
17
+
-**Debugging workflows**: Routes to `debug` prompt
17
18
-**Upgrading workflows**: Routes to `upgrade-agentic-workflows` prompt
18
19
-**Creating report-generating workflows**: Routes to `report` prompt — consult this whenever the workflow posts status updates, audits, analyses, or any structured output as issues, discussions, or comments
19
20
-**Creating shared components**: Routes to `create-shared-agentic-workflow` prompt
20
21
-**Fixing Dependabot PRs**: Routes to `dependabot` prompt — use this when Dependabot opens PRs that modify generated manifest files (`.github/workflows/package.json`, `.github/workflows/requirements.txt`, `.github/workflows/go.mod`). Never merge those PRs directly; instead update the source `.md` files and rerun `gh aw compile --dependabot` to bundle all fixes
21
22
-**Analyzing test coverage**: Routes to `test-coverage` prompt — consult this whenever the workflow reads, analyzes, or reports on test coverage data from PRs or CI runs
23
+
-**Rendering ASCII charts in markdown**: Routes to `asciicharts` guide — consult this whenever the workflow needs compact charts that render reliably in GitHub issues, comments, or discussions
22
24
-**CLI commands and triggering workflows**: Routes to `cli-commands` guide — consult this whenever the user asks how to run, compile, debug, or manage workflows from the command line, or when they need the MCP tool equivalent of a `gh aw` command
25
+
-**Reducing token consumption / cost optimization**: Routes to `token-optimization` guide — consult this whenever the user asks how to reduce token usage, lower costs, speed up workflows, or measure the impact of prompt changes with experiments
26
+
-**Choosing workflow architectures and design patterns**: Routes to `patterns` guide — consult this whenever the user asks for strategy, architecture, operating models, or pattern selection for agentic workflows
23
27
24
28
Workflows may optionally include:
25
29
@@ -31,7 +35,7 @@ Workflows may optionally include:
31
35
- Workflow files: `.github/workflows/*.md` and `.github/workflows/**/*.md`
@@ -93,7 +97,7 @@ When you interact with this agent, it will:
93
97
### Create a Report-Generating Workflow
94
98
**Load when**: The workflow being created or updated produces reports — recurring status updates, audit summaries, analyses, or any structured output posted as a GitHub issue, discussion, or comment
- "Create a shared component for Notion integration"
@@ -113,7 +117,7 @@ When you interact with this agent, it will:
113
117
### Fix Dependabot PRs
114
118
**Load when**: User needs to close or fix open Dependabot PRs that update dependencies in generated manifest files (`.github/workflows/package.json`, `.github/workflows/requirements.txt`, `.github/workflows/go.mod`)
- "Fix the open Dependabot PRs for npm dependencies"
@@ -123,7 +127,7 @@ When you interact with this agent, it will:
123
127
### Analyze Test Coverage
124
128
**Load when**: The workflow reads, analyzes, or reports test coverage — whether triggered by a PR, a schedule, or a slash command. Always consult this prompt before designing the coverage data strategy.
- "Create a workflow that comments coverage on PRs"
@@ -133,20 +137,44 @@ When you interact with this agent, it will:
133
137
### CLI Commands Reference
134
138
**Load when**: The user asks how to run, compile, debug, or manage workflows from the command line; needs the MCP tool equivalent of a `gh aw` command; or is in a restricted environment (e.g., Copilot Cloud) without direct CLI access.
- "How do I trigger workflow X on the main branch?"
140
144
- "What's the MCP equivalent of `gh aw logs`?"
141
145
- "I'm in Copilot Cloud — how do I compile a workflow?"
142
146
- "Show me all available gh aw commands"
143
147
148
+
### Token Consumption Optimization
149
+
**Load when**: The user asks how to reduce token usage, lower workflow costs, make a workflow faster or cheaper, or measure the impact of prompt or configuration changes.
- "How do I reduce the token cost of this workflow?"
155
+
- "My workflow is too expensive — how do I optimize it?"
156
+
- "How do I compare token usage between two runs?"
157
+
- "Should I use gh-proxy or the MCP server?"
158
+
- "How do I use sub-agents to reduce costs?"
159
+
- "How do I measure the impact of a prompt change?"
160
+
161
+
### Workflow Pattern Selection
162
+
**Load when**: The user asks for architecture, strategy, operating model selection, or pattern recommendations for building agentic workflows.
163
+
164
+
**Reference file**: `.github/aw/patterns.md`
165
+
166
+
**Use cases**:
167
+
- "Which pattern should I use for multi-repo rollout?"
168
+
- "How should I structure this workflow architecture?"
169
+
- "What pattern fits slash-command triage?"
170
+
- "Should this be DispatchOps or DailyOps?"
171
+
144
172
## Instructions
145
173
146
174
When a user interacts with you:
147
175
148
176
1.**Identify the task type** from the user's request
149
-
2.**Load the appropriate prompt** from the GitHub repository URLs listed above
177
+
2.**Load the appropriate prompt** from the repository paths listed above
150
178
3.**Follow the loaded prompt's instructions** exactly
151
179
4.**If uncertain**, ask clarifying questions to determine the right prompt
152
180
@@ -185,12 +213,12 @@ gh aw compile --validate
185
213
186
214
## Important Notes
187
215
188
-
- Always reference the instructions file at https://github.com/github/gh-aw/blob/v0.72.1/.github/aw/github-agentic-workflows.md for complete documentation
216
+
- Always reference the instructions file at `.github/aw/github-agentic-workflows.md` for complete documentation
189
217
- Use the MCP tool `agentic-workflows` when running in GitHub Copilot Cloud
190
218
- Workflows must be compiled to `.lock.yml` files before running in GitHub Actions
191
219
-**Bash tools are enabled by default** - Don't restrict bash commands unnecessarily since workflows are sandboxed by the AWF
192
220
- Follow security best practices: minimal permissions, explicit network access, no template injection
193
-
-**Network configuration**: Use ecosystem identifiers (`node`, `python`, `go`, etc.) or explicit FQDNs in `network.allowed`. Bare shorthands like `npm` or `pypi` are **not** valid. See https://github.com/github/gh-aw/blob/v0.72.1/.github/aw/network.md for the full list of valid ecosystem identifiers and domain patterns.
221
+
-**Network configuration**: Use ecosystem identifiers (`node`, `python`, `go`, etc.) or explicit FQDNs in `network.allowed`. Bare shorthands like `npm` or `pypi` are **not** valid. See `.github/aw/network.md` for the full list of valid ecosystem identifiers and domain patterns.
194
222
-**Single-file output**: When creating a workflow, produce exactly **one** workflow `.md` file. Do not create separate documentation files (architecture docs, runbooks, usage guides, etc.). If documentation is needed, add a brief `## Usage` section inside the workflow file itself.
195
223
-**Triggering runs**: Always use `gh aw run <workflow-name>` to trigger a workflow on demand — not `gh workflow run <file>.lock.yml`. `gh aw run` handles workflow resolution by short name, input parsing and validation, and correct run-tracking for agentic workflows. Use `--ref <branch>` to run on a specific branch.
196
-
-**CLI commands reference**: For a complete guide on all `gh aw` commands and their MCP tool equivalents (for restricted environments), see https://github.com/github/gh-aw/blob/v0.72.1/.github/aw/cli-commands.md
224
+
-**CLI commands reference**: For a complete guide on all `gh aw` commands and their MCP tool equivalents (for restricted environments), see `.github/aw/cli-commands.md`
description: Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.
4
+
---
5
+
6
+
# Agentic Workflows Router
7
+
8
+
Use this skill when a user asks to design, create, update, debug, or upgrade GitHub Agentic Workflows in this repository.
9
+
10
+
This skill is a dispatcher: identify the task type, load the matching workflow prompt/skill file, and follow it directly. Keep responses concise and ask a clarifying question if the correct prompt is unclear.
11
+
12
+
Read only the files you need:
13
+
Load these files from `github/gh-aw` (they are not available locally).
- Map CLI commands to MCP usage: `.github/aw/cli-commands.md`
77
+
- Choose workflow architecture and patterns: `.github/aw/patterns.md`
78
+
- Optimize token usage and cost: `.github/aw/token-optimization.md`
79
+
80
+
When the task involves OTEL, OTLP, traces, observability backends, or telemetry-driven analysis, also read and follow `skills/otel-queries/SKILL.md` after loading the matching workflow prompt or skill.
0 commit comments