CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-brainstorm

Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm or scope what to build. Not for executing already-specified work. Use ce-pov for a verdict on adopting a named external technology.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/ce-brainstorm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured orchestration overview that delegates detail to an extensive, verified reference bundle via an excellent phase-to-file table, with concrete artifact and config contracts. Its weaknesses are prose density with some redundant rule restatements, and a few key terms left undefined or unnamed in the body.

Suggestions

Split the overloaded "Done, on the brainstorm path" sentence into short bullet conditions and state the file-earning rule once instead of twice (Done and Lightweight paragraphs).

Name the rendering reference explicitly (markdown-rendering.md / html-rendering.md) instead of "the rendering reference" in the Phase 3 row.

Define the path tokens <type> and <topic> and the "Goal Capsule" / "Product Contract" section names where they are first used, or point to where they are defined.

DimensionReasoningScore

Conciseness

Everything is skill-specific policy with no re-teaching of known concepts, but the ~60-word "Done, on the brainstorm path" sentence and the "file is earned only by..." rule stated twice (Done paragraph and Lightweight paragraph) are convoluted and could be noticeably tightened — anchor 3 rather than 4.

3 / 5

Actionability

Concrete guidance throughout: exact artifact path pattern "<root>/plans/YYYY-MM-DD-HHMM-<type>-<topic>-plan.<md|html>", named frontmatter keys (artifact_contract: ce-unified-plan/v1), and exact config resolution with git rev-parse --show-toplevel. Minor gaps: "the rendering reference" is unnamed, and <type>/<topic> tokens and "Goal Capsule" are undefined in-body — anchor 4, not 5.

4 / 5

Workflow Clarity

The phase table gives a clear sequenced workflow (Phases 0–4) with per-phase read-first gates, and a named hard validation checkpoint ("do not declare it written or enter Phase 4 while any check fails" in the Ready for Planning Check). Not 5 because the check's actual contents and error-recovery loops are delegated to reference files rather than visible in-body.

4 / 5

Progressive Disclosure

A lean ~70-line overview with a phase table mapping each phase to its exact reference file and what that file carries; all referenced files verified to exist and effectively one level deep. Minor gaps: "the rendering reference" is not named, and several bundle files (bakeoff.md, publishing.md, visual-probes.md) are discoverable only via second-level references — anchor 4, not 5.

4 / 5

Total

15

/

20

Passed

Description

82%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: third-person voice, explicit what/when with concrete trigger phrases, and explicit boundaries against sibling skills (ce-plan implied, ce-pov named). The only weakness is that it names just one or two concrete actions rather than a fuller catalog of capabilities.

DimensionReasoningScore

Specificity

"Explore vague or ambitious ideas into a right-sized requirements-only unified plan" names the domain and one to two concrete actions with a concrete output artifact, but does not list several distinct concrete actions, matching anchor 3 rather than 4.

3 / 5

Completeness

It explicitly answers both what ("requirements-only unified plan") and when ("Use when the user wants to brainstorm or scope what to build") with concrete trigger phrases, and adds a negative boundary ("Not for executing already-specified work") — clearly anchor 5.

5 / 5

Trigger Term Quality

"brainstorm", "scope", "what to build", and "ideas" are phrases users would naturally say, giving good keyword coverage, though common synonyms like "flesh out an idea", "requirements", or "spec" are missing — anchor 4, not 5.

4 / 5

Distinctiveness Conflict Risk

"Not for executing already-specified work. Use ce-pov for a verdict on adopting a named external technology" explicitly disambiguates against sibling skills, giving a clear niche with distinct triggers and minimal conflict risk — anchor 5.

5 / 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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

EveryInc/compound-engineering-plugin

Path

skills/ce-brainstorm/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.