completion_proof
Skill2 starsChanged 3 months agoMITView on GitHub
Local report-only detector for completion claims without evidence markers (A11). Does not authenticate evidence or block builds.
In this repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- clean-cacheSkill
- agent-cacheSkill
- app_testSkill
- asset-qualitySkill
- auto_distillSkill
- auto-memorySkill
- auto_routerSkill
- benchSkill
- bootstrapSkill
- botte-proxySkill
- cacheSkill
- capabilitiesSkill
- cardinalSkill
- cavemanSkill
- checkupSkill
- clarificationSkill
- clusterSkill
- code_fingerprintSkill
- conductorSkill
- context_budgetSkill
- context_profilerSkill
- context_slicerSkill
- context_windowsSkill
- control_loopSkill
- cost_estimatorSkill
- cwe_kbSkill
- dag_optimizerSkill
- dashboardSkill
- decision-ladderSkill
- demoSkill
- diff_languageSkill
- directives_auditSkill
- docgenSkill
- docs_stewardSkill
- eventsSkill
- fallow_likeSkill
- fast_contextSkill
- fixSkill
- harness_deltaSkill
- hermes-bridgeSkill
- hf_provenanceSkill
- infra_advisorSkill
- ingestSkill
- llm_backendsSkill
- llm_mcpSkill
- loaderSkill
- mcp_gatewaySkill
- meta_harnessSkill
- metricsSkill
- migration_auditSkill
- monte_cristoSkill
- mousquetairesSkill
- nlp_deterministicSkill
- nn_auditSkill
- prefix-prunerSkill
- prefix_treeSkill
- preflightSkill
- prompt_improverSkill
- reportSkill
- The first 60 shown.
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
- Distinctive: line 20
No test execution, hash verification, or ingestion enforcement is performed.
≈ “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.
Files
Completion proof markers (A11)
Detects reports claiming completion without an associated evidence marker:
test_id, cmd_output_ref, artifact_hash, a passed validation with a
reference, or supported lexical markers in text reports.
python -m skills.completion_proof.cli path/to/report.json --json
python -m skills.completion_proof.test_completion_proofThis is a report-only heuristic. A non-empty reference may point to a
nonexistent file; lexical markers can also suppress a finding. The CLI returns
zero even when findings exist. Consumers must inspect errors and findings.
No test execution, hash verification, or ingestion enforcement is performed.
A separate opt-in --verify path now verifies receipt, log and source hashes
against a trusted digest supplied outside the report. See the
v1 verification contract. This does not change the legacy
marker audit. Add --strict to return nonzero unless verification succeeds;
the calling workflow must honor that exit status before closing its task.
The five finding fields describe evidence, estimated cost, expected benefit, risk, and a minimal suggested remedy. These are qualitative, not measurements.
See the replayable demonstration and its negative control before treating a clean report as verified success.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.