agentleFS
ultimatileultimatile/development-skills/skills/research-and-implement/SKILL.md

research-and-implement

Skill0 starsChanged 32 days agoMITView on GitHub

Work a GitHub issue end to end in two phases — research, then implement.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before research begins, settle the working branch and the root the change will be measured from.

    line 14
  2. Distinctive:

    Check current branch: git branch --show-current

    line 16
  3. Very specific:

    After Phase 1 settles and the user approves the (possibly review-revised) plan, execute /implement $ARGUMENTS, supplying the root Phase 0 …

    line 34

≈ “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

research-and-implement

End-to-end wrapper. Runs research (Phase 1) and implement (Phase 2) in sequence, with a branch and root baseline gate up front.

Issue: #$ARGUMENTS

PHASE 0 — BRANCH AND ROOT BASELINE

Before research begins, settle the working branch and the root the change will be measured from.

  1. Check current branch: git branch --show-current
  2. Determine the default branch as diff-root directs; step 3 compares the current branch against it.
  3. Decision gate:
    • On default branch → pick a conventional <type>/<issue#>-<slug> (feat/195-dmrg-envs, fix/187-arpack-info, chore/<slug>), create it, and proceed. Do not poll the user for the name — branch names are throwaway closed-PR metadata. Announce the chosen name in one line so the user can intervene if they object, then continue without waiting.
    • On a non-default branch → treat it as the intended branch and proceed. Only stop if the branch name plainly contradicts the issue (e.g., on feat/100-foo while working #200) — in that case announce the mismatch and ask.
  4. Once the branch is settled, record it (and any switch / creation action) so Phase 2 can pick it up unambiguously.
  5. Settle the root, on diff-root's terms: the branch this work merges into, as a bare branch name. The ref step 3 cut the branch from is not it — a local branch is routinely ahead of or behind what the work will merge into, and commits inherited that way must stay in every gate's scope because they land through the same PR. Take a root the caller supplied; with none, ask. Record it beside the branch, and state it: Phase 2 passes it on, and a caller continuing past this skill needs it for its own gates.

This phase exists to keep direct pushes off the default branch, and to keep every later gate measuring from the ref the work is actually against, by making both questions deterministic at the start. Default → branch automatically; do not block on the user for naming.

PHASE 1 — RESEARCH

Execute /research $ARGUMENTS.

The plan posted to the issue MUST include the Inconclusive / Deferred items section (or Inconclusive / Deferred items: none identified). This section is the discovery contract Phase 2 will enforce.

PHASE 2 — IMPLEMENT

After Phase 1 settles and the user approves the (possibly review-revised) plan, execute /implement $ARGUMENTS, supplying the root Phase 0 settled.

Phase 2 will halt rather than ad-hoc-patch any mid-implementation discovery that is not listed in the plan's discovery contract. If that happens, return to Phase 1 (or update the plan explicitly) before resuming.

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.