CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

provocation

Extract movement from a statement known to be false. Use when nobody can see past an obvious answer.

Quality

71%

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 ./hope/skills/provocation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 an exemplary instruction-only skill: lean, sequenced, with a genuine self-validation checkpoint and explicit routing to sibling skills. Its only minor gap is the absence of a worked example showing a false statement and the resulting assumption bullets.

DimensionReasoningScore

Conciseness

The body (~200 words) is lean and dense: every line instructs ("Label it false out loud, each time it appears", "Hand the named list back as short bullets, one assumption or closed option per line") with zero padding and no explanation of concepts Claude already knows. It fully matches anchor 5 — every token earns its place.

5 / 5

Actionability

As an instruction-only skill, the guidance is concrete and executable: choose a falsehood attacking the biggest assumption, label it false each time, walk toward it naming forced assumptions, return one-per-line bullets, discard the statement. It falls short of anchor 5 only because there are no worked examples (a sample false statement and its resulting bullet list) to make the common case copy-paste unambiguous.

4 / 5

Workflow Clarity

The sequence is clear and conditional branches are explicit: write the statement → walk toward it → built-in checkpoint ("If you catch yourself arguing that the statement does work... the walking ends there") → hand back bullets or the proposal → routing rules for adjacent situations. It matches anchor 4 (clear sequence with most checkpoints present); there is no error-recovery feedback loop needed for this non-destructive, single-turn task, so 5's checklist/loop requirements are not met.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no external references needed, and the content is organized into distinct, well-ordered paragraphs (setup, method, output, fallback, routing) that fully cover the skill. Per the rubric's simple-skill guideline this earns anchor 5 with well-organized structure alone.

5 / 5

Total

18

/

20

Passed

Description

41%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 has an unusual and distinctive niche with a present-but-vague trigger clause, yet both halves are phrased so abstractly that a user (or Claude routing skills) could not reliably tell what the skill concretely does or when to invoke it. It avoids generic fluff but sacrifices specificity for style.

Suggestions

State the concrete output in plain terms, e.g. "Write a deliberately false statement to expose hidden assumptions in an accepted answer, then return a bulleted list of those assumptions and closed-off options."

Replace the poetic trigger with natural user phrasing: add terms like "the team is stuck on one obvious answer", "everyone agrees too quickly", or "challenge the obvious solution".

Briefly enumerate the deliverable and the routing conditions (e.g. sibling skills judge/draft/elicit) so the description distinguishes this skill from its related family members.

DimensionReasoningScore

Specificity

"Extract movement from a statement known to be false" names the domain (deliberately false statements) but offers only a single, abstract action — "movement" is a metaphor, not a concrete capability like "extract text" or "fill forms". It sits at anchor 2 (domain named, minimal/generic actions) rather than 3, whose example requires 1-2 genuinely concrete actions.

2 / 5

Completeness

Both a "what" ("Extract movement from a statement known to be false") and a "Use when..." clause are present, so it clears the anchor-3 cap for a missing trigger. However the "what" is too metaphorical to count as a clear statement of what the skill does, and the "when" is a single poetic condition rather than concrete trigger phrases — placing it between anchors 3 and 4, but noticeably below the anchor-4 example in clarity on both halves.

3 / 5

Trigger Term Quality

The only trigger phrase is "Use when nobody can see past an obvious answer" — a condition a user would rarely voice naturally when they need this skill; there are no synonyms or plain-language keywords (e.g. "stuck", "obvious answer", "challenge assumptions"). It is above anchor 1 only because "obvious answer" gestures at a real trigger scenario, but it remains generic rather than the natural phrases users say.

2 / 5

Distinctiveness Conflict Risk

The niche is quite distinct — no other common skill is described as extracting movement via deliberately false statements — but the body reveals a family of closely related reasoning skills (judge, draft, elicit) with adjacent triggers, creating minor overlap risk. That matches anchor 4 (mostly distinct, minor overlap with closely related skills) rather than 5, which demands minimal conflict risk.

4 / 5

Total

11

/

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

saadshahd/moo.md

Path

hope/skills/provocation/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.