CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cf-sdlc-implement

Invoke when the user asks to implement, build, or write the code for a FEATURE — e.g. "implement", "write the code", "build this feature", "implement FEATURE with @cpt-* traceability". Thin preset binding the CODE artifact KIND, delegating implementation and review to the core cf-coding engine.

54

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/cf-sdlc-implement/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The body is a lean, dense delegation stub that sequences bootstrap-then-protocol cleanly, but everything it delegates to lives outside the bundle behind an unresolved path placeholder, and its own guidance is pseudocode rather than executable instruction.

Suggestions

Resolve the {cf-studio-path} placeholder to a concrete, checkable path (or explain how to resolve it in one line), so the LOAD instructions are actually followable.

Add brief section headers (e.g. "## Bootstrap", "## Protocol delegation") to organize the flat rule list and make the two-unit structure scannable.

State in one sentence what happens if a required file is missing (beyond "ALWAYS stop") — e.g. the exact stop/report behavior — so the stop condition is an actionable checkpoint rather than an implicit one.

DimensionReasoningScore

Conciseness

The ~30-line body is dense directives with no padding and no explanation of concepts Claude already knows; only minor tokens are questionable, such as the ask_tool_description definition of what a tool is and repeated ALWAYS-style meta-rules across both units — fitting the efficient-with-minor-trimmings anchor rather than the lean-every-token-earns-its-place anchor.

4 / 5

Actionability

The pdsl block is pseudocode rather than executable code, with concrete intent (LOAD required-bootstrap.md, RUN RequiredBootstrap, load implement.md as controlling protocol) but an unresolved placeholder ({cf-studio-path}) and no runnable commands — precisely the pseudocode-with-missing-key-details anchor, not the mostly-executable one.

3 / 5

Workflow Clarity

A two-unit sequence exists (bootstrap before any target workflow, then treat implement.md as controlling protocol) with traversal rules and a stop condition ("ALWAYS stop if any required fragment or rule cannot be followed"), but the actual steps and gates live in external files that are not part of the bundle, leaving checkpoints implicit — anchor 3, not 4.

3 / 5

Progressive Disclosure

References are clearly signaled via explicit LOAD statements, but they point outside the skill bundle ({cf-studio-path}/... with no references/, scripts/, or assets/ directories present), so the load-bearing instructions are unverifiable; the body itself is a flat rule list with no section headers — some structure, but not well-organized navigation, matching anchor 3 rather than 2 (references are not buried) or 4 (references resolve to nothing navigable).

3 / 5

Total

13

/

20

Passed

Description

66%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.

The description answers both what and when with genuinely natural trigger phrases, but its capability statement is dominated by ecosystem-internal jargon and its triggers are broad enough to collide with generic coding skills.

Suggestions

Rewrite the capability sentence in plain language, e.g. "Sets up the CODE artifact workflow, then delegates implementation and review steps to the core cf-coding engine protocol" — replacing jargon like "Thin preset binding the CODE artifact KIND".

Add one or two concrete, distinctive capabilities the skill actually performs (e.g. what the implement workflow produces: code changes plus review verification) so the what is more than pure delegation.

Narrow the trigger conditions so generic coding requests don't collide with this skill — e.g. scope to the cf-sdlc context or feature-level implementation requests, and drop bare "implement" as a trigger.

DimensionReasoningScore

Specificity

The only concrete capability statement is "delegating implementation and review to the core cf-coding engine"; the listed actions ("implement, build, or write the code") are trigger phrasings rather than capabilities, and "Thin preset binding the CODE artifact KIND" is internal jargon, matching the domain-plus-1-2-actions anchor rather than the several-specific-actions anchor.

3 / 5

Completeness

Both parts are present: an explicit when ("Invoke when the user asks to implement, build, or write the code for a FEATURE") and a what ("Thin preset binding the CODE artifact KIND, delegating implementation and review"), but the what relies on unexplained internal terminology ("CODE artifact KIND", "cf-coding engine"), keeping it below the fully explicit anchor.

4 / 5

Trigger Term Quality

Includes natural phrases users would actually say ("implement", "write the code", "build this feature") plus a system-specific trigger ("implement FEATURE with @cpt-* traceability"), but misses common synonyms like "develop" or "create the feature", so it falls short of comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

Triggers like "implement" and "write the code" would match almost any coding skill, giving real overlap risk, but the "@cpt-* traceability" and "cf-coding engine" markers carve a distinct niche within the cf ecosystem, fitting the somewhat-specific anchor rather than the very-broad one.

3 / 5

Total

14

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

constructorfabric/gears-frontx

Path

.claude/skills/cf-sdlc-implement/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.