CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-a-feature

Add a new feature, put work behind a feature flag, roll something out (per organization, for everyone, cloud or self-hosted), revert or kill a feature, or make a big change to existing behavior such as a new engine. Use BEFORE writing the feature code, and when finishing or removing a rollout.

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

Passed

No findings from the security scan

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.

Excellent workflow-oriented content: every instruction is executable and codebase-specific, the rollout sequence includes explicit validation checkpoints and kill-switch recovery loops, and nothing wastes tokens on general knowledge. The only structural improvement would be moving the gating API enumeration into a one-level-deep reference file to keep SKILL.md a pure overview.

DimensionReasoningScore

Conciseness

The body is lean and entirely codebase-specific — registry path, resolve precedence, pnpm command behavior, CI-rejected patterns — with no explanation of concepts Claude already knows and no padded sections, matching the 5 anchor where 'every token earns its place'.

5 / 5

Actionability

Guidance is fully executable: a copy-paste-ready TypeScript declaration block, exact commands ('pnpm features:sync', 'pnpm dev:den:mysql', 'pnpm features:check'), exact call signatures with arguments (organizationFeatureEnabled(orgId, "newThing", { userId }), requireFeature("newThing")), and concrete file lists to commit — matching the 5 anchor.

5 / 5

Workflow Clarity

A clear four-phase sequence (declare → make safe to kill → gate → roll out) with a numbered rollout containing explicit checkpoints and error-recovery loops ('checking errors as you go', 'Anything wrong: Turn off everywhere... Fix, restore, continue') and validation gates ('Run pnpm features:check before pushing', 'Do not stop after Helm generation if the contract step fails') — matching the 5 anchor.

5 / 5

Progressive Disclosure

The single file is well-sectioned with clear headers and no nested or buried references, but the seven-variant gating API enumeration in section 3 is reference-like material inlined in the overview; at ~110 lines a one-level-deep split would fit the 5 anchor's 'content appropriately split' better, so the 4 anchor's 'minor organization gaps' is the best fit.

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.

A strong description that comprehensively enumerates the feature lifecycle (add, gate, roll out per scope, revert/kill) in third-person imperative style, with an explicit and concrete 'Use when' trigger clause. The only weakness is that 'add a new feature' is a broadly phrased trigger with minor overlap risk against generic feature-development requests.

DimensionReasoningScore

Specificity

The description lists multiple concrete lifecycle actions — 'Add a new feature, put work behind a feature flag, roll something out (per organization, for everyone, cloud or self-hosted), revert or kill a feature' — giving comprehensive coverage from creation through removal, which matches the 5 anchor rather than the 4 anchor's 'minor gaps in coverage'.

5 / 5

Completeness

It explicitly answers both 'what' (the full set of feature lifecycle actions) and 'when' with a concrete Use-when clause: 'Use BEFORE writing the feature code, and when finishing or removing a rollout', exactly matching the 5 anchor.

5 / 5

Trigger Term Quality

Natural trigger phrases are comprehensively covered with synonyms: 'feature flag', 'roll something out', 'revert or kill a feature', plus scoping variations ('per organization', 'for everyone', 'cloud or self-hosted') users would naturally say, matching the 5 anchor's inclusion of synonyms rather than the 4 anchor's 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

'Add a new feature' and 'make a big change to existing behavior' are broad phrases that overlap with general coding requests, but 'feature flag', 'roll something out', and 'kill a feature' pin it to a distinct rollout niche — fitting the 4 anchor's 'minor overlap risk' better than the 5 anchor's minimal conflict risk.

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

different-ai/openwork

Path

.opencode/skills/add-a-feature/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.