CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 lean, highly actionable body with executable validation scripts, gated workflows, and a pointer-first structure. Its weaknesses are duplicated sections ('NO toca' vs 'Anti-creep rules', repeated auto-chain triggers) and a few artifact-writing steps that describe rather than show.

Suggestions

Merge the 'NO toca' and 'Anti-creep rules' sections into one boundary/enforcement section — they repeat the same four prohibitions nearly verbatim.

Inline a minimal skeleton or field list for 07-merge.md's '5 secciones cementadas' (or point explicitly to the template's section names) so the merge workflow is fully executable without locating the template.

Move the auto-chain trigger examples out of the 'Comandos típicos' table or cross-reference the 'Auto-chain rule' section to remove the duplicated trigger enumeration.

DimensionReasoningScore

Conciseness

The body is dense and table-driven with no padding of known concepts, but the 'NO toca' and 'Anti-creep rules' sections repeat ~4 items nearly verbatim, and auto-chain triggers appear in both the 'Auto-chain rule' section and the 'Comandos típicos' table — mostly efficient but should be tightened.

3 / 5

Actionability

Provides a copy-paste-ready Step 0 bash gate script, specific commands ('python scripts/generate_project_map.py', 'git mv docs/product/stories/{id} docs/archive/{YYYY}/stories/{id}'), and a concrete Skill tool invocation shape; minor gaps remain, e.g. 'Escribir 07-merge.md con las 5 secciones cementadas' describes the artifact without showing its schema inline.

4 / 5

Workflow Clarity

Bootstrap has an explicit validation gate (Step 0 scan with GREEN condition, deferred/open branching, and recovery redirects like 'si PROJECT-MAP.md no existe → sugerir /project-audit'), the auto-chain rule validates WIP caps + deps + state-machine with enumerated exceptions, and the destructive merge is a numbered checklist gated on 'auditor APPROVED + CHECKPOINTS.md' with STOP+redirect on schema violations — explicit validation, feedback loops, and checklists.

5 / 5

Progressive Disclosure

Pointer-first with per-surface token costs, on-demand drill-down, and a final 'Referencias' section of one-level-deep pointers; however, no bundle files exist in the skill directory (referenced paths like scripts/generate_project_map.py resolve to unverifiable project files), and state-machine/merge detail is inlined rather than split, leaving minor organization gaps.

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 specific, trigger-rich description that explicitly states what the skill does and when to activate it, with concrete paths and named sibling skills. Its main weakness is jargon density (SSoT, paradigm v4, método Luana) and a few generic trigger words that could overlap with sibling skills.

Suggestions

Add the common user phrases from the body's command table ('qué tenemos', 'merge', 'nueva idea', 'regen') to the 'Activa' trigger list for fuller synonym coverage.

Briefly gloss ecosystem jargon (e.g., 'SSoT funcional' → 'single source of truth for functional docs') so the description is self-contained outside the método Luana project context.

DimensionReasoningScore

Specificity

Lists several concrete actions with specific paths and target skills ('carga docs/PROJECT-MAP.md + docs/product/checkpoint.md + docs/product/BACKLOG.md', 'Owner: docs/product/{outcomes,stories,capabilities,modules}/', 'Auto-chain a /po-ux, /po, /ux-agentico, /architect, /dev-team, /auditor'), matching the 'several specific actions; minor gaps' anchor — capabilities like merge and regen from the body are absent, so coverage is not comprehensive.

4 / 5

Completeness

The 'what' is explicit ('PM único del proyecto (single-brand) — owner del SSoT funcional' plus concrete duties) and the 'when' is an explicit enumerated trigger clause ('Activa: ...') equivalent to a 'Use when...' clause, matching the anchor for clearly answering both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

'Activa: /pm, estado proyecto, backlog, story, outcome, capability, learning, refinemos X, qué hacemos hoy' gives good natural-phrase coverage, but common body-level variations ('qué tenemos', 'merge', 'regen', 'nueva idea') are missing, so it falls short of the comprehensive-with-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

A clear PM niche with handoff boundaries ('Auto-chain a /po-ux, /po, ...') makes it mostly distinct, but generic trigger words like 'backlog', 'story', and 'learning' carry minor overlap risk with the closely related sibling skills it chains to.

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.

Validation — 13 / 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

Path

claude/skills/pm/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.