Mola-maker/mstack / skills/m-goal
m-goal
VerifiedLong-running goal loop: goal file, checkpoints, stop rules, mandatory closeout. Use for run-until-done work, 别停/一直做到完成.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.6 KB |
| references/closeout.md | markdown | 2.2 KB |
| references/goal-file-format.md | markdown | 4.3 KB |
| scripts/goal-preflight.test.mjs | script | 4.0 KB |
| scripts/goal-state.mjs | script | 7.8 KB |
| scripts/goal-state.test.mjs | script | 8.8 KB |
references/closeout.md
View on GitHub# Closeout content (m-goal)
Read this at step 6 and whenever a loop exits. The `## Closeout` section always contains these fields, in order:
- **status** — `done`, `failed`, `interrupted`, or `budget-exhausted`.
- **objective** — the goal's one-line objective.
- **result** — what was actually achieved against the acceptance criteria, with the evidence (commands + output) for each.
- **unfinished** — every sub-goal or criterion still open, and why.
- **known-issues** — errors that survived retries, one line each (what broke, what was tried).
- **lessons** — repeatable traps or decisions worth encoding in structure (principle 10); write nothing if there are none.
- **gate** — one line each for `m-deslop` / `m-verify` / `m-review`: pass or fail plus the proving command. A goal with a failed gate is not `done`.
- **Attention** — filled by a different model than the one that ran the loop: anything the next session must not miss. `无` is a valid entry.
- **resume-hint** — for `failed`/`interrupted`/`budget-exhausted`: what to read to resume (the goal file path, last checkpoint, blocker).
## Amend, never rewrite
Acceptance criteria can be amended but never silently edited. A refuted criterion stays verbatim under `## Amendments`, with the reason and the measured evidence that refuted it; an amendment without evidence is invalid. The closeout is checked against the active criteria only.
If the outcome was `done`, mark all sub-goals complete and note the reviewer verdict. If not, leave the goal file intact so a later `m-goal` resume or `m-handoff` continues from the last checkpoint. Never claim completion without a written closeout. m-handoff only links to this closeout; it never writes one.
## Gate verdicts
`m-review` passes iff it has no confirmed in-scope finding and no axis marked `issues`; Unconfirmed and Cleared items do not block. Record the verdict line it printed in the `gate` field.
## Ruling lines
Every judgement call the skill does not cover goes in the goal file's checkpoint table as `Ruling: decision | reason | cost if wrong` (in the `decision` cell, with the three parts separated by `|` escaped as `/`). Read them back when writing `result` and `known-issues`.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |