Conciseness

The ~46-line body is lean and load-bearing: compact shape attributions ('MADR / Nygard shape', 'Google SRE shape', 'Diátaxis how-to') instead of explaining what postmortems or ADRs are, and no padded sections. It assumes Claude's competence, matching anchor 5; anchor 4 would require noticeable over-explanation that could be trimmed, which is not the case here.

Actionability

Concrete naming patterns ('0001-feature-name.md'), explicit status flows ('draft → fcp → accepted/rejected'), a copy-paste-able call ('write({ document: { path, template: "<name>" } })'), and conditional agent directives ('more than 14 days, surface it') make the guidance mostly executable. The gap keeping it below anchor 5: template names for proposals, decisions, specs, and postmortems are never enumerated — only the three guide templates are named.

Workflow Clarity

The lifecycle is clearly sequenced with an explicit flow diagram and status gates (accepted, derived, when things break), and the table routes each task type to a sibling skill. It sits at anchor 4 rather than 5 because there are no validation or recovery checkpoints (e.g., what to check before freezing a decision or advancing a status), though no destructive/batch cap applies.

Progressive Disclosure

The body appropriately keeps per-folder rules inline while delegating workflow detail one level deep to sibling skills, clearly signaled via the workflow table — good structure per anchor 4. It misses anchor 5 because template discovery is implicit (names scattered across sections rather than a clear index), and no bundle files exist to verify the referenced paths against.

Specificity

The description lists several concrete elements ('proposals → decisions → specs → postmortems, plus guides', 'doc lifecycle, status flows, and per-folder agent behaviors'), but describes structure more than actions, leaving minor coverage gaps. It exceeds anchor 3 (which expects only 1-2 concrete actions) but falls short of anchor 5's comprehensive coverage.

Completeness

It explicitly answers both what ('How to work in a Software Lifecycle project... carries the doc lifecycle, status flows, and per-folder agent behaviors') and when ('Read when the project has these folders, or when asked how this project is organized'). The when-clause is explicit with concrete trigger conditions, matching anchor 5 rather than the less-explicit anchor 4.

Trigger Term Quality

Natural terms like 'postmortems', 'spec', 'proposal', and 'how this project is organized' give good keyword coverage, but common synonyms users would say (RFC, ADR, runbook) are absent from the description. Solid anchor 4: good coverage with a few natural terms missing, not the comprehensive synonym coverage of anchor 5.

Distinctiveness Conflict Risk

It explicitly disambiguates from the platform skill ('Complements the platform `open-knowledge` skill; does not replace it') and routes the five workflows to sibling skills. However, terms like postmortem, spec, and proposal naturally overlap with those sibling skills' triggers, so it is 'mostly distinct with minor overlap risk' (anchor 4) rather than minimal-conflict anchor 5.