CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

context-index

Regenerates the project's context index (index.yaml) from the YAML frontmatter across every context file, grouping entries by typology (findings/plans/goals/evidence/guides/follow-ups/handovers/merge-requests/tickets/decisions/notes/research), and validates that each file carries the required frontmatter fields. Also computes which active files are ready to work on, from optional typed `blocks`/`blocked-by` dependency links (scripts/context-ready.sh). Use when the index is stale, context files were added, renamed, or removed, a pre-commit gate blocks a commit because a context file is missing frontmatter, or someone asks what's ready/unblocked/blocked across the context backlog. Do not use it to create new context files (use create-context-file instead), to hand-edit the index, or as a substitute for fixing frontmatter at the source.

Quality

89%

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

81%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 highly actionable: concrete commands with expected outputs, a validate-fix-regenerate loop with explicit stop conditions, and a real one-level-deep reference file for deep detail. Its weakness is redundancy — the hand-edit and derived-index rules are each repeated across three sections, and split-index mechanics are inlined in both the body and the reference.

Suggestions

State the 'never hand-edit the index / frontmatter is the source of truth' rule once (e.g. in Mindset or the Anti-Patterns section) and reference it from the other sections instead of restating it three times.

Trim the split-index detail in the body to the decision the agent must make at run time (use --split or not, reader rule) and push flag-by-flag mechanics and gate wiring into references/regeneration-reference.md.

Collapse the three References rows that point to regeneration-reference.md into one row (or one row per distinct file) so the navigation table reflects the actual bundle structure.

DimensionReasoningScore

Conciseness

Quotes: "NEVER hand-edit the index" (Mindset), "Do not edit the generated index by hand — it is fully regenerated" (When Not to Use), and a full "NEVER edit the generated index by hand" anti-pattern section — the same rule stated three times, and the "index is derived / frontmatter is the source of truth" idea likewise recurs. The content is project-specific rather than padded with things Claude already knows, but the repetition is more than the minor trimming a 4 would allow, and far from the several padded sections of a 2.

3 / 5

Actionability

Quotes: "./scripts/check-context-frontmatter.sh .context/**/*.md", "Expected result: `OK: <N> file(s) validated against schema`", "./scripts/regenerate-context-index.sh --split --no-aggregate". Every workflow is copy-paste-ready with its expected result stated, the exact frontmatter shape is given as a schema block, and the common cases (check, validate, regenerate, ready/blocked) are each covered.

5 / 5

Workflow Clarity

Quotes: "**Verify:** the script prints nothing and exits 0. If it lists files, those are invisible to the index until fixed" and "**Stop if:** it reports files excluded on stderr; go back to step 2 rather than treating the run as complete". The procedure is clearly sequenced with explicit validation checkpoints and a feedback loop that routes failures back to the fix step — exactly the 5 anchor.

5 / 5

Progressive Disclosure

Quotes: the References table rows "Technical details, parsing rules, exit codes, and CI integration | [Regeneration Reference](references/regeneration-reference.md)" — a real, one-level-deep bundle file, clearly signaled with when-to-use guidance. It is not 5 because the 264-line body inlines substantial split-index detail ("## Split index (opt-in)", "### Reader rule") that also lives in the reference, and three table rows all point to the same file — minor organization gaps rather than misplacement.

4 / 5

Total

17

/

20

Passed

Description

92%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 is explicit, concrete, and well-scoped: it names the exact artifacts and actions, gives multiple natural trigger situations, and actively disambiguates from its companion skill. The only weakness is a slightly technical stretch (the typology enumeration and field-name jargon) that keeps trigger coverage just short of comprehensive.

DimensionReasoningScore

Specificity

Quotes: "Regenerates the project's context index (index.yaml) from the YAML frontmatter across every context file", "validates that each file carries the required frontmatter fields", "computes which active files are ready to work on, from optional typed `blocks`/`blocked-by` dependency links". Multiple specific concrete actions (regenerate, group by typology, validate, compute readiness) with comprehensive coverage; it is not 4 because there are no meaningful gaps in the action list.

5 / 5

Completeness

Quotes: "Regenerates the project's context index (index.yaml)… and validates that each file carries the required frontmatter fields" (what) and "Use when the index is stale, context files were added, renamed, or removed, a pre-commit gate blocks a commit…" (when). Both questions are answered explicitly with concrete trigger phrases, plus negative scope guidance.

5 / 5

Trigger Term Quality

Quotes: "Use when the index is stale, context files were added, renamed, or removed, a pre-commit gate blocks a commit because a context file is missing frontmatter, or someone asks what's ready/unblocked/blocked". Good natural-phrase coverage of likely user utterances, but stretches like the 12-item typology enumeration and backticked field names are technical rather than natural, and a few synonyms (e.g. "rebuild the index") are absent — so not the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

Quotes: "Do not use it to create new context files (use create-context-file instead), to hand-edit the index, or as a substitute for fixing frontmatter at the source". A clear niche (index regeneration/validation/readiness over context files) with explicit disambiguation from the companion skill, so conflict risk is minimal.

5 / 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

pantheon-org/tekhne

Path

skills/project-mgmt/context-index/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.