CtrlK
BlogDocsLog inGet started
Tessl Logo

orch-change-feature

Orchestrate altering an existing, working feature to new desired behavior — update its tests to the new spec, change the implementation to match, review, and gated commit. Use when behavior is not broken but should be different.

68

Quality

85%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured wrapper skill with excellent conciseness, clear gated workflow, and clean organization. The only weak spot is actionability: it delegates actual execution to the orch-pipeline engine, so it is not standalone-executable despite its specific guidance.

Suggestions

Add a one-line inline note on the concrete first action Claude can take without opening the engine (e.g., the exact command or file to touch first) so the skill is partially executable standalone.

Make the dependency on orch-pipeline's own validation/retry loop explicit (e.g., 'the engine runs validate→fix→retry; this skill only sets phase mask and gates') so the reader knows where the feedback loop lives.

DimensionReasoningScore

Conciseness

Lean and dense with no explaining of concepts Claude already knows; every section (When to Use, Operation settings, How It Works, Example) earns its place; not a 2 because there is no unnecessary padding to tighten.

3 / 3

Actionability

Gives concrete directives (phase mask sequence, named gates, first-move rule, when to add security-reviewer) and a concrete example, but execution is externalized to the referenced orch-pipeline engine rather than being copy-paste executable on its own; not a 3 because it is not fully self-contained/executable, not a 1 because guidance is specific rather than vague.

2 / 3

Workflow Clarity

Clear sequence (phase mask 0→…→6, numbered How It Works) with explicit validation checkpoints (Gate 1 plan/changed-test approval, Gate 2 pre-commit, shown as [GATE 2: confirm] in the example); not a 2 because checkpoints are explicit rather than implicit or missing.

3 / 3

Progressive Disclosure

Under-50-line body with well-organized sections and one clearly-signaled one-level reference (../orch-pipeline/SKILL.md); per the guideline, simple skills with no needed external references can score 3 on well-organized sections alone.

3 / 3

Total

11

/

12

Passed

Description

85%

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 states concrete actions and an explicit Use-when trigger while distinguishing the skill from its siblings. Its main weakness is trigger-term coverage, relying on more abstract phrasing rather than the natural words users tend to say.

Suggestions

Add the natural verbs users say into the description, e.g. "Use when the user asks to change, adjust, or make a working feature behave differently (e.g. 'instead of X do Y')."

Optionally include a concrete keyword cluster ("change, adjust, tweak, make it also…") alongside "should be different" to broaden trigger matching.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "update its tests to the new spec, change the implementation to match, review, and gated commit" — matching the anchor for several specific concrete actions; not a 2 because it goes beyond naming a domain plus a few actions.

3 / 3

Completeness

Explicitly answers both what (the four named actions) and when ("Use when behavior is not broken but should be different"); not a 2 because the trigger is explicit rather than merely implied.

3 / 3

Trigger Term Quality

Contains relevant terms ("altering...feature", "should be different") but omits the natural phrasings users actually say ("change", "adjust", "instead of X do Y"), which appear only in the body; not a 3 because coverage of common variations is thin, not a 1 because some relevant keywords are present.

2 / 3

Distinctiveness Conflict Risk

"behavior is not broken but should be different" carves a clear niche distinct from fixing broken features and adding new ones, making conflict with sibling skills unlikely.

3 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
affaan-m/ECC
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.