CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paseo-committee

Form a committee of two high-reasoning agents to step back, do root cause analysis, and produce a plan. Use when stuck, looping, tunnel-visioning, or facing a hard planning problem.

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 ./.agents/harness/adapters/antigravity/skills/paseo-committee/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

41%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.

The body is a generated redirect stub: maximally token-efficient but containing none of the skill's actual substance. All actionable guidance, workflow sequencing, and validation are outsourced to an external `~/.agents/skills/` path that is not shipped in the bundle and does not resolve here, leaving the skill non-self-contained.

Suggestions

Inline the core workflow in SKILL.md — how to form the two-agent committee, the root-cause analysis prompts to run, and the expected plan format — instead of delegating 100% of the content to an external file.

Replace the absolute `~/.agents/skills/paseo-committee/SKILL.md` pointer with bundle-relative references (e.g., `references/committee.md`) shipped inside the skill so the skill is self-contained and portable.

Add explicit validation/verification steps (e.g., criteria for when the root cause is confirmed or the plan is complete) so the multi-step process has checkpoints.

DimensionReasoningScore

Conciseness

The body is two lines — a maintenance comment and one redirect instruction — with zero padding and no explanation of concepts Claude already knows, so every token earns its place; even the anchor 4 example retains trimmable over-explanation that is absent here.

5 / 5

Actionability

The only concrete guidance is a single instruction to "Load and follow the shared skill at `~/.agents/skills/paseo-committee/SKILL.md`" — a specific path, so above anchor 1's pure abstraction — but every executable step for the actual task is delegated elsewhere, and the referenced path is an absolute external location that is not part of the skill bundle (and does not resolve in this environment), matching anchor 2's minimal guidance missing the specific steps.

2 / 5

Workflow Clarity

The description implies a multi-step process (form a committee, run root cause analysis, produce a plan) but the body contains no sequence, no steps, and no validation whatsoever — "Load and follow" is not a workflow — matching anchor 1's "steps missing or incoherent; no sequence".

1 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/ directories) and the single reference points to an absolute path outside the skill directory rather than a bundle-relative file, so the skill is a bare redirect with no overview content of its own; it avoids anchor 1 (no wall of text or multi-level nesting) but the buried external reference and absent structure match anchor 2 better than anchor 3's "some structure".

2 / 5

Total

10

/

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 strong description: it states concrete capabilities in third person, includes an explicit and natural "Use when" trigger clause, and carves out a recognizable niche. Its only weaknesses are minor — a few missing trigger synonyms and slight overlap risk with general planning skills.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Form a committee of two high-reasoning agents", "do root cause analysis", and "produce a plan" — which goes beyond the 1-2 actions of anchor 3, but mechanics like how the committee operates or what the plan contains are unspecified, so it falls short of anchor 5's comprehensive coverage.

4 / 5

Completeness

It explicitly answers both questions: the "what" (form a committee, do root cause analysis, produce a plan) and the "when" via a concrete "Use when stuck, looping, tunnel-visioning, or facing a hard planning problem" clause, matching the anchor 5 pattern of explicit what-and-when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Triggers "stuck", "looping", "tunnel-visioning", and "hard planning problem" are phrases a user would naturally say, giving good keyword coverage, but common variations like "spinning", "going in circles", "rabbit hole", or "overthinking" are missing, so it does not reach anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The committee-of-two-agents framing combined with root-cause analysis when stuck is a fairly distinct niche, but the "hard planning problem" trigger could overlap with generic planning or brainstorming skills, leaving minor conflict risk rather than anchor 5's minimal risk.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

phatblat/dotfiles

Path

.agents/harness/adapters/antigravity/skills/paseo-committee/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.