CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

decide

Turns a hard product or career decision into a one-page decision memo with the eigenquestion, options, pre-mortem with kill criteria, reversibility rating, a named decider and a review date. Use when you ask 'how should we decide', 'should we build or kill this', 'one-way door or two-way door', 'run a pre-mortem', 'we keep going in circles', 'quit or pivot', or want to grade a decision doc. Draws on 396 insights from 177 Lenny's Podcast guests, led by Annie Duke, Shreyas Doshi and Shishir Mehrotra.

77

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 dense, highly actionable skill body: routing table, step-by-step plays with done-when checkpoints, a copy-paste deliverable template, and a grading rubric, with zero filler. The only structural weakness is partial duplication between the inline plays and references/frameworks.md.

Suggestions

Trim or move the Receipts section's quotes into references/quotes.md (where they already live) to reduce body-to-reference duplication.

Consider compressing the play steps that are restated nearly verbatim in references/frameworks.md, keeping the body's routing table plus done-when criteria and pointing to the reference for full steps.

DimensionReasoningScore

Conciseness

No padding and no explanation of concepts Claude already knows — every line carries podcast-specific procedure (e.g., "Set a 90-day clock or it never happens"), assuming competence throughout; sections like Receipts and Red Flags each carry unique content rather than restatement.

5 / 5

Actionability

Fully actionable instruction-only guidance: numbered steps per play, literal prompts ("imagine this has failed miserably six months from now"), a copy-paste markdown deliverable template, and a grading rubric with 1/3/5 anchors — no execution gaps.

5 / 5

Workflow Clarity

Clear sequence (Diagnose → Pick the play via routing table → Run it → Deliverable → Grade) with explicit validation checkpoints: "Done when:" criteria per play, "stop at the first clear answer" in Play E, and the same-one-sentence-decision completion check.

5 / 5

Progressive Disclosure

References are real, one level deep, and well-signaled ("references/frameworks.md — every framework in this skill, how to run it"; both files verified to exist with matching content), but the body inlines all eight plays at full procedural detail while frameworks.md restates and expands them — some content could be offloaded, which is a minor organization gap rather than a fully appropriate split.

4 / 5

Total

19

/

20

Passed

Description

96%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.

An exemplary description: concrete deliverable components, seven natural trigger phrases, and explicit what/when structure in third-person voice. The only weakness is slight overlap risk with adjacent prioritization/strategy skills via a couple of broad trigger phrases.

DimensionReasoningScore

Specificity

The description enumerates the exact deliverable components ("one-page decision memo with the eigenquestion, options, pre-mortem with kill criteria, reversibility rating, a named decider and a review date") plus a second concrete action ("grade a decision doc"), matching the comprehensive-coverage anchor rather than the minor-gaps anchor below it.

5 / 5

Completeness

Both what (a one-page decision memo with named components) and when ("Use when you ask '…'" with concrete trigger phrases) are explicit, mirroring the top anchor's structure exactly; the when-clause is already specific, so it is not the 4 anchor.

5 / 5

Trigger Term Quality

Seven natural quoted trigger phrases users would actually say ("how should we decide", "one-way door or two-way door", "run a pre-mortem", "quit or pivot", "grade a decision doc") give comprehensive coverage with synonyms across product and career framings; no material natural terms are missing.

5 / 5

Distinctiveness Conflict Risk

A clear decision-making niche with distinctive triggers, but "we keep going in circles" and "should we build or kill this" could plausibly fire for closely related skills the body itself names (prioritize, strategy) — minor overlap risk rather than minimal, so the 4 anchor fits better than the 5.

4 / 5

Total

19

/

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

menkesu/awesome-pm-skills

Path

skills/decide/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.