CtrlK
BlogDocsLog inGet started
Tessl Logo

pm

PM único del proyecto (single-brand) — owner del SSoT funcional. Pointer-first: carga docs/PROJECT-MAP.md + docs/product/checkpoint.md + docs/product/BACKLOG.md (si existe) en bootstrap. Owner: docs/product/{outcomes,stories,capabilities,modules}/, docs/learnings/, docs/architecture/, docs/domains/. Hereda paradigm v4 (10 estados macro) del método Luana. Auto-chain a /po-ux, /po, /ux-agentico, /architect, /dev-team, /auditor via Skill tool inline. Activa: '/pm', 'estado proyecto', 'backlog', 'story', 'outcome', 'capability', 'learning', 'refinemos X', 'qué hacemos hoy'.

64

Quality

79%

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 ./claude/skills/pm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A tightly structured, action-oriented PM skill body with real scripts, a state-machine vocabulary, and validated destructive workflows. The chief gaps are slight redundancy between the two prohibition sections and references pointing to project-level files rather than bundled skill assets.

Suggestions

Collapse the 'NO toca' and 'Anti-creep rules' sections into one to remove the duplicated prohibition list and recover tokens.

Add an explicit failure-recovery branch to the merge workflow (e.g., what to do if 06-audit gherkin-matrix is not all PASS or CHECKPOINTS.md verdict is not APPROVED).

Verify the referenced regen scripts and .claude/rules/*.md files exist within or alongside the skill bundle, since progressive disclosure assumes referenced paths are reachable.

DimensionReasoningScore

Conciseness

The body is dense and table-driven, assumes Claude knows the method, and avoids concept over-explanation; the only trimmable redundancy is the 'NO toca' and 'Anti-creep rules' sections restating the same prohibitions.

4 / 5

Actionability

Executable bash for the Step 0 gate scan and Step 1 load, a concrete command→action table, and a 7-step merge workflow with real paths give mostly copy-paste-ready guidance, with minor gaps where commands depend on scripts not bundled here (generate_project_map.py, generate_backlog.py).

4 / 5

Workflow Clarity

Bootstrap (Step 0 gate → Step 1 → Step 2) and the merge workflow are clearly sequenced with validation gates (Step 0 STOP on violation, merge requires auditor APPROVED + CHECKPOINTS.md), but the destructive merge lacks an explicit failure-recovery loop.

4 / 5

Progressive Disclosure

Well-organized sections with a pointer-first philosophy and a 'Referencias' list of one-level-deep external docs; no bundle files exist to verify, and some referenced material (regen scripts, .claude/rules/*) lives outside the skill rather than in a bundled references/ dir.

4 / 5

Total

16

/

20

Passed

Description

83%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.

A dense, role-specific description that successfully pairs concrete owned surfaces and chained skills with an explicit natural-language trigger list. Main weakness is heavy internal jargon (SSoT, paradigm v4, método Luana) that obscures the 'what' for anyone outside the method.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'carga docs/PROJECT-MAP.md + checkpoint.md + BACKLOG.md', 'Owner: docs/product/{outcomes,stories,capabilities,modules}/', 'Auto-chain a /po-ux, /po...' — with only minor jargon-based gaps (SSoT, paradigm v4) rather than a full enumeration of capabilities.

4 / 5

Completeness

Both 'what' (single-brand PM owner of the functional SSoT, pointer-first bootstrap, owns named paths, auto-chains) and 'when' (explicit 'Activa:' trigger list) are answered clearly with concrete trigger phrases, satisfying the top anchor.

5 / 5

Trigger Term Quality

The 'Activa:' clause surfaces natural phrases users would say — '/pm', 'estado proyecto', 'backlog', 'refinemos X', 'qué hacemos hoy' — giving good keyword coverage, though a few common synonyms/variations are not enumerated.

4 / 5

Distinctiveness Conflict Risk

The single-brand PM niche and role-specific triggers (backlog, story, outcome, capability, learning) are mostly distinct, with only minor overlap risk against the sibling skills it chains to (/po, /po-ux, /architect, /dev-team, /auditor).

4 / 5

Total

17

/

20

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

13

/

16

Passed

Repository
alpacapurpura/luana-method
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.