CtrlK
BlogDocsLog inGet started
Tessl Logo

build-something-fast

Use when the user gives a short, rough, or one-line idea for an app, tool, script, or feature and wants it built end-to-end without being asked clarifying questions. Triggers - "build me...", "create an app that...", "I want a tool for...", "quick app for...", minimal specs, seed ideas.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 exceptionally actionable, well-sequenced workflow with strong validation checkpoints and feedback loops. Its weaknesses are mild verbosity from cross-referenced repetition and a monolithic single-file structure with no progressive disclosure of its detailed templates and rules into reference files.

Suggestions

Move the reusable templates (the 04-ledger.md template, the per-story Gherkin/checklist schema) into reference files under references/ and link to them one level deep, splitting the 165-line monolith.

De-duplicate the attempt-accounting rules: state them once in 4.1.6 and have 4.2.4 reference that section instead of restating the max-attempts totals.

Tighten the Adversary respawn/death rules in 4.1.5c–d into a compact fallback table to reduce token weight without losing the fail-closed guarantees.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive and does not explain concepts Claude already knows, but at ~165 lines it includes repetition (attempt accounting appears in both 4.1.6 and 4.2.4) and elaborate Adversary respawn rules that could be tightened, matching the "mostly efficient but could be tightened" anchor rather than "every token earns its place".

2 / 3

Actionability

It gives fully executable guidance: an exact ledger template, a mandatory COMMAND:/EXIT_CODE: evidence contract, and concrete commands such as `git log --grep "^US-<n>:"` and `git show --stat`, making the workflow copy-paste ready.

3 / 3

Workflow Clarity

Steps 1–4 are explicitly sequenced with validation checkpoints (evidence-proven ticks, Adversary fresh-context verification, regression/commit-integrity/intent-drift sweeps) and clear fail→fix→re-prove feedback loops, the exemplar for this dimension.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a single 165-line SKILL.md; it is well-sectioned with clear headings, but content that could be split out (the ledger template, the per-story schema, the Adversary rules) is all inline, fitting the "some structure but content that should be separate is inline" anchor rather than the simple-skill exception (which applies only under 50 lines).

2 / 3

Total

10

/

12

Passed

Description

90%

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 is strong: third-person voice, an explicit "Use when" trigger clause, and natural quoted trigger phrases users would actually say. Its only weak spot is specificity, since the action side collapses to a single "built end-to-end" action rather than enumerating multiple concrete actions.

DimensionReasoningScore

Specificity

Names the domain ("app, tool, script, or feature") and a concrete core action ("built end-to-end without being asked clarifying questions"), but the action side is a single end-to-end build rather than a comprehensive list of distinct actions, so it stops short of the level-3 anchor.

2 / 3

Completeness

An explicit "Use when the user gives a short, rough, or one-line idea..." clause answers "when", and "wants it built end-to-end without being asked clarifying questions" answers "what", satisfying both halves with explicit triggers.

3 / 3

Trigger Term Quality

Quotes natural phrases a user would actually say — "build me...", "create an app that...", "I want a tool for...", "quick app for...", plus "minimal specs" and "seed ideas" — giving strong coverage of real trigger language.

3 / 3

Distinctiveness Conflict Risk

The one-line-seed → autonomous end-to-end build with no clarifying questions is a clear niche with distinct triggers, unlikely to fire for ordinary coding or debugging requests.

3 / 3

Total

11

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
cindulasai/build-something
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.