agentleFS
richkuorichkuo/rk-skills/skills/fableplan-work-on-issue/SKILL.md

fableplan-work-on-issue

Skill50 starsChanged 5 days agoMITView on GitHub

Use when the user wants a GitHub issue planned by Fable 5.1 and then implemented in one shot, without validation or a review loop — "fableplan-work-on-issue", "fableplan and work on #N", "plan #N with fable then implement it". Runs the fableplan planning phase (Fable 5.1 produces and posts an implementation plan to the issue), then hands off to work-on-issue, which implements the plan in an isolated worktree and opens a PR that closes the issue. Stops at the open PR — it does not request review or loop. The trimmed counterpart to validate-fableplan-loop (no validate-issue step, no @claude review cycle).

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Follow fableplan-loop steps 0 through 3 with these changes:

    line 19

≈ “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

fableplan-work-on-issue

Chain fableplan → work-on-issue into one autonomous run: Fable 5.1 plans the implementation for a GitHub issue (plan posted to the issue), then work-on-issue implements that plan in an isolated worktree and opens a PR that closes the issue.

It is fableplan-loop with the review loop removed: the handoff goes to work-on-issue, which ends at the open PR. It has no validate-issue step and no score gate: fableplan always runs.

Input

Same as fableplan-loop's Input section, including the required issue, the owner/repo#N record, and the optional targetBranch.

Steps

Follow fableplan-loop steps 0 through 3 with these changes:

  • Step 1 (fableplan): instruct fableplan to use the harness suffix fableplan-work-on-issue in the posted comment's attribution footer.
  • Step 2 (handoff): invoke the work-on-issue skill instead of work-on-issue-loop (Skill tool, skill: work-on-issue). The explicit owner/repo#N pass-through and the plan pointers (scratchpad file and posted issue comment) apply unchanged, and deviations follow work-on-issue step 2's plan-deviation policy, each named in the PR body. work-on-issue runs its full process and ends at the open PR. Requesting review is out of scope for this skill. If the user wants the PR driven through review to convergence, point them at fableplan-loop, validate-fableplan-loop, or a separate fix-pr-review-loop run; do not trigger review here.
  • Step 3 (report): in place of fableplan-loop's terminal-state list, relay work-on-issue's final summary (the worktree/branch, what was implemented, the verification result, the commit SHA, the PR URL, and that it closes the issue), prefixed with one line covering the head of the chain: plan posted (comment URL). If work-on-issue stopped at one of its own gates instead of opening a PR, report why it stopped; never imply a PR exists when it does not. Cap the whole report at 55 words and 5 sentences, plain simple English in ASD-STE100; apply the Response Style rules in CLAUDE.md/AGENTS.md.

Red Flags — STOP

fableplan-loop's Red Flags table applies, reading "work-on-issue" for "work-on-issue-loop", with one change: its review row inverts.

SituationAction
Tempted to trigger @claude review or loop on the PR after it opensDo not; this skill ends at the open PR. Point the user at fableplan-loop or fix-pr-review-loop if they want review driven to convergence

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.