agentleFS
Sign inStart free
tonmoy007tonmoy007/forge-plugins/skills/forge-feedback/SKILL.md

forge-feedback

Skill2 starsChanged 5 months agoMITView on GitHub

Run Stage 10 of the Forge pipeline — feedback triage. Use when the user

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 2 are distinctive, and 8 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If it exits non-zero, STOP: present its message verbatim and do not proceed — the prior stage must be completed first (or use …

    line 27
  2. Very specific:

    Read pipeline/state.md — confirm Forge project.

    line 31
  3. Distinctive:

    Ask the user to provide feedback items if none are present in the conversation.

    line 32
  4. Very specific:

    Check pipeline/09-monitor/health-report.md for any system signals to include.

    line 33
  5. Very specific:

    Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/load-profile.py --cwd .

    line 34
  6. Very specific:

    Read agents/triage.md to load the Triage Specialist persona.

    line 38
  7. Very specific:

    Read all available feedback: user input, monitoring signals, pipeline/10-feedback/ if it exists.

    line 40
  8. Distinctive:

    Follow the Triage workflow: classify, assign severity, recommend action, prioritize.

    line 41
  9. Very specific:

    Write pipeline/10-feedback/feedback-log.md (every incoming item, verbatim) and pipeline/10-feedback/triage.md (classified + prioritized) …

    line 42
  10. Very specific:

    Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 10 to mark Stage 10 active.

    line 44

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/forge:feedback — Feedback Triage

When to Use

  • User says /forge:feedback
  • User has user feedback, bug reports, or feature requests to process
  • User wants a prioritized action list from incoming signals
  • Working in a Forge project at Stage 9 or 10

Pre-flight Check

Entry gate (REQ-GATE-ENTRY-001) — before adopting the persona, verify the prior stage's artifact exists:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py preflight --stage 10

If it exits non-zero, STOP: present its message verbatim and do not proceed — the prior stage must be completed first (or use /forge:force-advance to skip intentionally).

  1. Read pipeline/state.md — confirm Forge project.
  2. Ask the user to provide feedback items if none are present in the conversation.
  3. Check pipeline/09-monitor/health-report.md for any system signals to include.
  4. Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/load-profile.py --cwd . --stage 10 to surface any project-type triage overrides (e.g., classes of feedback specific to the project type — UX regressions for fullstack, API contract breaks for API, regressions in train→serve parity for ML).

Steps

  1. Read agents/triage.md to load the Triage Specialist persona.
  2. Adopt that persona — you are now the Triage Specialist.
  3. Read all available feedback: user input, monitoring signals, pipeline/10-feedback/ if it exists.
  4. Follow the Triage workflow: classify, assign severity, recommend action, prioritize. Use any profile-specific categories from pre-flight to tag items.
  5. Write pipeline/10-feedback/feedback-log.md (every incoming item, verbatim) and pipeline/10-feedback/triage.md (classified + prioritized) per the Output Contract.
  6. Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 10 to mark Stage 10 active.

Verification

After running, confirm:

  • pipeline/10-feedback/feedback-log.md exists with all incoming feedback items
  • pipeline/10-feedback/triage.md exists with FB-IDs, classifications, and severities
  • Critical and high items have specific remediation steps
  • pipeline/state.md shows current_stage: 10

Next Step

Derive the hint from the canonical stage table — never hardcode it (REQ-NEXTHINT-001, single source of truth). Run the helper and present its output to the user verbatim:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py next-hint --stage 10

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free