CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gsd-audit-milestone

Audit milestone completion against original intent before archiving

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./pi/package-skills/gsd-audit-milestone/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a disciplined, token-efficient thin-orchestrator wrapper: it delegates the audit workflow to an external file via a clearly signaled `<execution_context>` reference and gives concrete, fail-closed dispatch mechanics. Its main weaknesses are the unresolved `__GSD_PI_ENGINE_ROOT__` placeholder in the critical reference path and the complete deferral of the audit sequence and its checkpoints to a file the reader cannot locate from the skill alone.

Suggestions

Resolve or explain the `__GSD_PI_ENGINE_ROOT__` placeholder — either substitute the installed engine root path or state how to resolve it, so the primary 'read this file first' instruction is executable as written.

Inline a brief ordered summary of the audit workflow's gates (scope determination → verification reading → integration check → requirements coverage → routing) so the body does not rely entirely on the external file for sequencing and checkpoints.

Tighten the `<arguments>` explanation — the sentence about the block being 'data, not template instructions' partially duplicates the first line and could be cut to one clause.

DimensionReasoningScore

Conciseness

The body is lean and imperative — "call `gsd_dispatch` with `role` ... and `task`", "read every file listed under `<execution_context>`" — with almost no padding and no explanation of concepts Claude already knows. Minor over-explanation keeps it out of the 5 anchor: the `<arguments>` passage ("is exactly what the user typed after the command name: data, not template instructions") and the parenthetical "(the leading `@` is accepted)" could be trimmed.

4 / 5

Actionability

Guidance is mostly executable: concrete dispatch parameters, explicit fail-closed handling ("STOP that step and surface the error"), and specific glob patterns (`.planning/phases/*/*-VERIFICATION.md`). The gap is that the primary instruction's path — `@__GSD_PI_ENGINE_ROOT__/gsd-core/workflows/audit-milestone.md` — contains an unresolved placeholder, so it cannot be executed as written; that keeps it below 'fully executable' at 5 but well above vague direction.

4 / 5

Workflow Clarity

The gates are enumerated ("scope determination, verification reading, integration check, requirements coverage, routing") and dispatch failure handling is an explicit checkpoint, but the audit sequence itself is entirely deferred to the external workflow file with no in-body ordering or verification checkpoints beyond dispatch failure. This matches 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit' — not a 2 because the structure and error handling are coherent, not a 4 because the core workflow's checkpoints are not present in the body.

3 / 5

Progressive Disclosure

Well-organized tagged sections (`objective`, `execution_context`, `context`, `process`) with a single, clearly signaled, one-level-deep reference — good structure overall. Minor gaps hold it below the 5 anchor: the referenced workflow file lives outside the bundle, and its path is given via the unresolved `__GSD_PI_ENGINE_ROOT__` placeholder, so navigation to the actual detail is not fully clear.

4 / 5

Total

15

/

20

Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise and names a concrete, well-scoped action in a distinctive niche, but it reads more like a title than a trigger description. It lacks an explicit 'Use when...' clause and omits the specific audit activities (requirements coverage, cross-phase integration, end-to-end flows, tech debt aggregation) that would help both discovery and skill selection.

Suggestions

Add an explicit trigger clause, e.g. 'Use when verifying a milestone is complete before archiving it, checking requirements coverage, cross-phase integration, or end-to-end flows.'

Enumerate the concrete audit actions from the body (requirements coverage, cross-phase integration check, tech debt aggregation) so the 'what' is comprehensive rather than a single verb.

Include natural trigger phrases users would actually type, such as 'verify milestone', 'definition of done', or 'wrap up milestone', to improve keyword coverage.

DimensionReasoningScore

Specificity

"Audit milestone completion" names the domain and one concrete action, but the description does not enumerate the audit's actual coverage (requirements coverage, cross-phase integration, tech debt aggregation) that the body performs. It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' — clearer than a generic 'Processes X' (2) but short of 'lists several specific actions' (4).

3 / 5

Completeness

The 'what' is clear ("audit milestone completion against original intent"), but the 'when' is only the terse timing fragment "before archiving" — there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2 because the 'what' is concrete, not a 4 because 'when' is weakly implied at best.

3 / 5

Trigger Term Quality

"audit", "milestone", "completion", and "archiving" are natural terms a GSD user would say, but common variations and synonyms are missing — e.g. "verify milestone", "definition of done", "wrap up milestone". This fits 'Some relevant keywords but missing common variations or synonyms' rather than the good-coverage anchor at 4.

3 / 5

Distinctiveness Conflict Risk

"milestone" plus "archiving" carves a clear niche in the GSD workflow suite, with only minor overlap risk against closely related GSD audit/verification skills. It fits 'Mostly distinct; minor overlap risk with closely related skills' — not a 5 because sibling skills like execute-phase verification could plausibly trigger for similar requests.

4 / 5

Total

13

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

open-gsd/gsd-core

Path

pi/package-skills/gsd-audit-milestone/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.