agentleFS
mystilleefmystilleef/spae-framework/skills/spae-verify/SKILL.md

spae-verify

Skill2 starsChanged 15 days agoMITView on GitHub

- STATE.json reads phase: verify: judge the implementation against SPEC.md. - Judge the implemented workstream against every SPEC.md requirement as the final arbiter; record every hard block in VERIFY.md. - On Pass, complete the workstream (phase: done); on Revision required, route it to phase: spec. Read only what the verdict requires: - .spae/current/STATE.json; references/STATE.md holds field reference, directives, and snapshots. - .spae/current/SPEC.md. - .spae/current/PLAN.md: task IDs and Scope fields. - Repository source, tests, docs, configuration, and logs the workstream changed,…

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 4 are distinctive, and 10 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 10

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read only what the verdict requires:

    line 25
  2. Very specific:

    Never read .spae/current/VERIFY.md.

    line 34
  3. Very specific:

    Read SPEC.md in full; capture every R-NNN into a coverage checklist.

    line 46
  4. Very specific:

    Read PLAN.md task Scope fields to bound workstream changes.

    line 48
  5. Very specific:

    Run the project checks and every SPEC.md Testing strategy command.

    line 56
  6. Very specific:

    Write STATE.json per the references/STATE.md exit snapshot matching the verdict.

    line 92
  7. Very specific:

    Write scope: write only .spae/current/VERIFY.md and .spae/current/STATE.json.

    line 116
  8. Very specific:

    Version control and release: never execute git mutations (staging, commits, branches, tags, pushes) or release operations.

    line 124
  9. Distinctive:

    Autonomy: never ask users for input or clarification mid-execution.

    line 127
  10. Very specific:

    State schema: never introduce STATE.json fields outside references/STATE.md.

    line 131
  11. Very specific:

    Every R-NNN judged against cited automated evidence.

    line 148
  12. Very specific:

    Every finding matching a Hard block or Soft finding item—workstream-added bloat included—carries that tag.

    line 149
  13. Distinctive:

    Keep prose terse while ensuring clarity.

    line 167
  14. Distinctive:

    Use lists and sub-lists for long sentences and dense paragraphs.

    line 170

≈ “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

Verify (SPAE)

When to use

  • STATE.json reads phase: verify: judge the implementation against SPEC.md.

Goal

  • Judge the implemented workstream against every SPEC.md requirement as the final arbiter; record every hard block in VERIFY.md.
  • On Pass, complete the workstream (phase: done); on Revision required, route it to phase: spec.

Input

Read only what the verdict requires:

  • .spae/current/STATE.json; references/STATE.md holds field reference, directives, and snapshots.
  • .spae/current/SPEC.md.
  • .spae/current/PLAN.md: task IDs and Scope fields.
  • Repository source, tests, docs, configuration, and logs the workstream changed, for analysis.

Never read .spae/current/VERIFY.md; SPEC.md holds every requirement.

Workflow

  1. GATE—Make no writes:
    • Parse .spae/current/STATE.json; self-heal missing metadata: version ("1.0"), workstream (target directory name), status ("active"); PERSIST writes the healed fields.
    • Halt on any Halt conditions entry.
  2. ORIENT—State goal in one sentence:
    • SPEC.md and PLAN.md stay unmodified; directly modify no source or tests; write nothing before PERSIST.
    • Read SPEC.md in full; capture every R-NNN into a coverage checklist.
    • Read PLAN.md task Scope fields to bound workstream changes.
  3. PLAN—Declare the evidence map:
    • Read references/verification-guide.md and references/shell-command-guide.md.
    • Map each R-NNN to the evidence that proves it: a Testing strategy command, a project check, or source.
    • Halt on any Halt conditions entry.
  4. ACT—Gather evidence and label findings:
    • Run the project checks and every SPEC.md Testing strategy command.
    • Judge each R-NNN against command output, workstream changes, and source.
    • Label each finding with exactly one tag:
      • Hard block—drives Revision required; cite reproducible evidence:
        • Missing or incorrect required behavior, a contract break, or a regression.
        • A project-check failure the workstream causes.
        • A spec defect: an R-NNN no available automated evidence proves, such as one needing human presence or tooling the repository never declares.
      • Soft finding—never a verdict input:
        • Absent test coverage of explicit required behavior.
        • An unsafe optimization.
        • Speculative abstraction, defensive bloat, or complexity no R-NNN grounds, cited from workstream changes—never a hypothetical risk or stylistic preference.
      • Observation—never a verdict input: thin edge-case coverage, an ambiguous requirement, a minor deviation outside SPEC.md scope, an unrequested guardrail, a theoretical risk, an Out of scope residual risk, or a check failure the workstream doesn't cause.
    • Head each finding with the R-NNN it concerns, else none.
    • On any Hard block, draft VERIFY.md per references/VERIFY.md.
    • Apply Directives and Constraints.
  5. VERIFY—Loop over Verification criteria for the verdict and the VERIFY.md draft:
    • For each failure: return to ACT, complete the evaluation, then re-enter VERIFY.
    • Exit only when every criterion passes.
    • Halt only on a Halt conditions entry.
  6. PERSIST—Write in order:
    • On a Revision required verdict, write .spae/current/VERIFY.md, replacing any prior copy.
    • Write STATE.json per the references/STATE.md exit snapshot matching the verdict.
    • Re-read STATE.json; on a mismatch against Verification state criteria, rewrite and re-read before REPORT.
    • On a Pass verdict, delete .spae/current/VERIFY.md when present, then remove the .spae/current symlink.
  7. REPORT—Emit result following result directives and using result template:
    • Result by re-read phase: done→Pass, spec→Revision required; a halt→Failed.
    • List each Hard block, then each Soft finding, then each Observation under Findings.

Directives

  • Optimize for agent, token, and context efficiency.
  • Refine and optimize VERIFY.md for agent consumption: agents read it for varied purposes, with no memory of this run; keep it self-contained, explicit, and token-dense; make each Hard block actionable without repeating the investigation.
  • Consult references/prose-protocol.md before drafting VERIFY.md.

Constraints

  • Write scope: write only .spae/current/VERIFY.md and .spae/current/STATE.json; on Pass, delete VERIFY.md and the .spae/current symlink; forbid all other writes. Byproducts of a command run for evidence, such as a formatter's rewrites, never count as this phase's writes; never run a command for its write effect outside this scope. Read source code only for analysis.
  • Phase boundary: judge the whole workstream; complete it or hand off work to /spec.
  • Version control and release: never execute git mutations (staging, commits, branches, tags, pushes) or release operations. Never stage or commit .spae/.
  • Autonomy: never ask users for input or clarification mid-execution; halts and failures stop autonomously. Never perform or request human execution, an attended or interactive terminal, or human presence.
  • State schema: never introduce STATE.json fields outside references/STATE.md.
  • Halt conditions: halt without writing; report Failed with a diagnostic under Findings:
    • .spae/current missing or dangling.
    • STATE.json missing or holds unparseable JSON syntax.
    • STATE.json phase other than verify.
    • SPEC.md or PLAN.md missing.
    • A PLAN.md task absent from tasks or reading other than "done".
    • Evidence can't run for a cause outside the repository: a broken external dependency or an environment failure.
  • Scope control: judge only SPEC.md requirements and workstream-caused regressions; add no requirement or verdict input beyond them.

Verification

  • Every R-NNN judged against cited automated evidence.
  • Every finding matching a Hard block or Soft finding item—workstream-added bloat included—carries that tag; every other finding carries Observation.
  • Verdict reads Pass only with zero Hard block findings; any Hard block yields Revision required.
  • On Revision required, the VERIFY.md draft matches references/VERIFY.md: every finding headed by its R-NNN, else none; every Hard block with File, Expected, Actual, and reproducible Evidence.
  • No VERIFY.md finding requests human execution, an attended or interactive terminal, or human presence.
  • STATE.json matches the references/STATE.md exit snapshot for the verdict.
  • This phase wrote no file outside Write scope.

Result directives

  • Minimum words. Maximum signal.
  • Keep prose terse while ensuring clarity.
  • Optimize prose for agent, token, and context efficiency.
  • Split actions, findings, and summaries into terse bullet points.
  • Use lists and sub-lists for long sentences and dense paragraphs.
  • Emit result template as live markdown—never in a code fence.
  • Output nothing outside template.
  • Source every SPAE Status value from confirmed re-read, never from working memory of intent.

Result template

<!-- prettier-ignore-start -->
### Execution Summary

- **Actions**:
  - [Terse list of actions taken]
- **Files**:
  - [Terse list of affected files]
- **Findings**:
  - [Terse list of notable findings]
- **Summary**:
  - [Terse list of summary of changes]

> **`SPAE` Status** • `[workstream-name]`
> **Result**: [Pass | Revision required | Failed]
> **Next Phase**: `/spec`  _(if revision required)_
<!-- prettier-ignore-end -->

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.