agentleFS
3orionkings3orionkings/forge/skills/forge-with-docs/SKILL.md

forge-with-docs

Skill0 starsChanged 19 days agoMITView on GitHub

Use when the user wants Forge planning grounded in an existing domain model, glossary, or ADR set, with those living documents updated as decisions settle. Use plain forge when no documentation alignment is needed. Do not use for review of already-written code or trivial changes.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Load the domain: Read CONTEXT.md (or the project's equivalent glossary/domain model) and any ADRs before the first question.

    line 14
  2. Very specific:

    Don't skip the doc load — grilling without the domain model is just /forge.

    line 46
  3. Distinctive:

    Don't let docs drift from decisions.

    line 47
  4. Distinctive:

    Don't add a routing or commit gate here.

    line 48
  5. Distinctive:

    Don't restate Act-3/4 procedure.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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-WITH-DOCS — Grill Against the Domain Model, Then Build

Act 1 variant: the same relentless interview as /forge, but stress-tested against the project's existing domain model and glossary — and the docs are updated as decisions crystallise, not afterwards.

Unique to this skill

  1. Load the domain. Read CONTEXT.md (or the project's equivalent glossary/domain model) and any ADRs before the first question.
  2. Grill with the docs in hand. One question at a time, recommending an answer for each; explore the codebase rather than asking what the code can answer. Additionally:
    • challenge each proposal against established terminology — if the plan reuses a term differently, resolve it before proceeding;
    • sharpen fuzzy terms into definitions the glossary can hold;
    • stress-test with concrete scenarios, not abstractions;
    • cross-reference the code for drift between canon and reality.
  3. Update the docs inline. As a decision settles, write it: new or changed glossary entries into CONTEXT.md, and a dated ADR for each contestable architectural choice (context · decision · consequences).
  4. Lock the plan into PLAN.md exactly as /forge Act 1 does, then hand to Act 2 (/forge-review mechanics) for adversarial review.

Then: execution is NOT this skill's business

Acts 2–4 run exactly as in ../forge/SKILL.md. This skill adds no gate of its own. In particular it does not impose a routing approval step: routing follows the active profile like everywhere else — under sprint the overlay or default executor is applied automatically with one line recorded and no Gate-2 wait.

Canonical references

../forge/ROUTING-POLICY.md (routing) · ../forge/profiles/ (cadence) · ../forge/ENGINE.md (engine, templates, admission) · ../forge/references/ (detail, on demand)

What NOT to do

  • Don't skip the doc load — grilling without the domain model is just /forge.
  • Don't let docs drift from decisions; write them as they settle.
  • Don't add a routing or commit gate here. The profile owns cadence.
  • Don't restate Act-3/4 procedure.

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.