CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tc

Track technical changes with structured records, a state machine, and session handoff. Usage: /tc <init|create|update|status|resume|close|export|dashboard> [args]

Quality

75%

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 ./.gemini/skills/tc/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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, token-efficient dispatcher that gives executable commands and validation checkpoints for all eight subcommands. The main defects are a script-path inconsistency between the stated location and the actual commands, thin error-recovery guidance, and a hedged approval-recording step.

DimensionReasoningScore

Conciseness

The body is a lean dispatcher: exact commands with flags, terse numbered steps, a compact menu, five Iron Rules, and three one-line Related Skills pointers. No concepts Claude already knows are explained and no section is padded — every token earns its place, matching anchor 5.

5 / 5

Actionability

Each subcommand has a copy-paste-ready invocation with exact script path, flags, and argument placeholders (e.g. "python3 engineering/skills/tc-tracker/scripts/tc_create.py --root . --name ... --json"), which is near anchor 5. It is held to anchor 4 because of a concrete inconsistency — line 23 states "All scripts live at `engineering/tc-tracker/scripts/`" while every command actually uses `engineering/skills/tc-tracker/scripts/` (one path is wrong) — and step 5 of `close` hedges with "if your script version supports it" instead of giving a definitive command.

4 / 5

Workflow Clarity

Every subcommand is a clearly numbered sequence with explicit validation checkpoints: `update` says "If exit code is non-zero, surface the error verbatim", `close` verifies status is `tested` and warns on pending tests before transitioning, `export` re-validates every record, and the Iron Rules act as a checklist ("Validate before reporting success"). This fits anchor 4; it is not anchor 5 because error recovery is thin — on failure the guidance is to stop ("do not retry blindly") with no fix-and-retry loop, and the `resume` step 4 update (a `--note`/`--reason` with no field change) may itself be rejected by the validator it tells the user to trust.

4 / 5

Progressive Disclosure

As a single-file dispatcher with no bundle files (no references/, scripts/, or assets/ present), the body is well-organized by subcommand headers and defers deep detail — schema reference, lifecycle diagrams, handoff format — to the full `engineering/tc-tracker` SKILL.md, and Related Skills are one-line, one-level pointers. This matches anchor 4 ("Good structure; most content is appropriately placed; references mostly clear"); not anchor 5 because the pointer to the full skill is a bare path rather than a clearly signaled link, and the flag reference for `tc_update.py` is inlined wholesale where a short reference table would ease navigation.

4 / 5

Total

17

/

20

Passed

Description

55%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 gives a clear picture of what the skill does and enumerates its subcommands, but it omits any explicit trigger guidance for when to use it and lacks natural synonyms that would help it fire on real user phrasing. It also has moderate overlap risk with changelog and debt-tracking skills.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when the user asks to track a technical change, record a change's status, or resume work from a previous session handoff.'

Include natural synonyms and user-facing vocabulary in the description (e.g. 'change tracking', 'audit trail', 'pick up where you left off') to improve trigger-term coverage.

Add a distinguishing phrase (e.g. 'per-change audit trail with lifecycle states, complementing changelogs') to reduce overlap risk with changelog and tech-debt trackers.

DimensionReasoningScore

Specificity

The description names the domain ("Track technical changes") and lists several concrete actions via the subcommand enumeration "<init|create|update|status|resume|close|export|dashboard>", plus mechanisms "structured records, a state machine, and session handoff". This matches anchor 4 ("Lists several specific actions; minor gaps in coverage") rather than anchor 3, since more than 1-2 concrete actions are explicitly stated; it falls short of anchor 5 because what each subcommand actually does is not described.

4 / 5

Completeness

The "what" is clear ("Track technical changes with structured records, a state machine, and session handoff"), but there is no "Use when..." clause or equivalent trigger guidance; the "Usage:" line documents invocation syntax, not when the skill applies. Per the judging guideline, a missing 'Use when...' clause caps completeness at 3 ("Has a clear 'what' but 'when' is missing or only weakly implied").

3 / 5

Trigger Term Quality

Relevant keywords like "technical changes", "track", "state machine", and "session handoff" are present, but common natural variations users would say are missing (e.g. "change tracking", "audit trail", "pick up where I left off", "deployed"). This matches anchor 3 ("Some relevant keywords but missing common variations or synonyms"); not anchor 4 because the synonym coverage is thin, and not anchor 2 because the terms given are domain-specific rather than generic.

3 / 5

Distinctiveness Conflict Risk

"Track technical changes" carves out a niche, but the phrase overlaps with adjacent skills a user might intend, such as changelog generation, tech-debt tracking, or task/todo trackers — overlap the body itself acknowledges via Related Skills. This fits anchor 3 ("Somewhat specific but could still overlap with similar skills"); not anchor 4 because no distinguishing trigger phrases distinguish it from those neighbors.

3 / 5

Total

13

/

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

alirezarezvani/claude-skills

Path

.gemini/skills/tc/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.