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

forge-resolve

Skill2 starsChanged 5 months agoMITView on GitHub

Run Stage 11 of the Forge pipeline — issue resolution and hotfixes. Use

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 2 are distinctive, and 9 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.

  • 9

    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 26
  2. Very specific:

    Read pipeline/state.md — confirm Forge project.

    line 30
  3. Distinctive:

    Read the triage report and surface the critical/high items to the user before starting.

    line 32
  4. Very specific:

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

    line 33
  5. Very specific:

    Read agents/resolver.md to load the Resolver persona.

    line 37
  6. Very specific:

    Read pipeline/10-feedback/triage.md.

    line 39
  7. Very specific:

    Follow the Resolver workflow: reproduce → root cause → targeted fix → regression test → commit.

    line 40
  8. Very specific:

    Update pipeline/11-resolve/hotfixes.md with each resolved item, and record any deferred (P2/P3) items in …

    line 41
  9. Very specific:

    Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 11 after first resolution.

    line 43
  10. Distinctive:

    After each resolution, confirm:

    line 47
  11. Very specific:

    Commit uses fix(FB-XXX): format

    line 52

≈ “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:resolve — Resolution & Hotfix

When to Use

  • User says /forge:resolve
  • User wants to fix bugs, apply hotfixes, or address triage items
  • Working in a Forge project at Stage 10 or 11

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 11

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. Confirm pipeline/10-feedback/triage.md exists. If not: "Complete Stage 10 first (/forge:feedback)."
  3. Read the triage report and surface the critical/high items to the user before starting.
  4. Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/load-profile.py --cwd . --stage 11 to surface any project-type resolution overrides (e.g., library projects: every fix must consider semver impact and backward compatibility).

Steps

  1. Read agents/resolver.md to load the Resolver persona.
  2. Adopt that persona — you are now the Resolver.
  3. Read pipeline/10-feedback/triage.md. Start with the highest severity item.
  4. Follow the Resolver workflow: reproduce → root cause → targeted fix → regression test → commit. Apply profile-specific constraints (e.g., for library projects, classify each fix as patch/minor/major and document any breaking-change migration).
  5. Update pipeline/11-resolve/hotfixes.md with each resolved item, and record any deferred (P2/P3) items in pipeline/11-resolve/backlog-updates.md.
  6. Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/state-manager.py advance --to 11 after first resolution.

Verification

After each resolution, confirm:

  • Root cause documented in pipeline/11-resolve/hotfixes.md
  • Deferred items recorded in pipeline/11-resolve/backlog-updates.md
  • Regression test added and passing
  • Full test suite passing
  • Commit uses fix(FB-XXX): format

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 11

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.

Reviews can't be read right now.

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