CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

coach

Learning telemetry, strategy, and schedule — retention stats, calibration, grader audit, n-of-1 experiments, HTML dashboard. Use for "how am I doing", weekly check-ins, strategy questions, auditing the grader, or adjusting how Engram teaches.

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

77%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 with strong, validated workflows and copy-paste commands, but it is over-long for a SKILL.md: repeated rationale anecdotes hurt conciseness, and the monolithic single-file structure with no bundle references limits progressive disclosure.

Suggestions

Trim version-history anecdotes ("Found by a dogfood", the v0.8.0 fired-rate story) to one-line justifications or move them to a CHANGELOG; the directive rule is what Claude needs, not the discovery narrative.

Split each sub-command's detailed branches (audit, experiment, contribute) into reference files under references/ and keep SKILL.md as a concise overview pointing one level deep, which would raise progressive disclosure.

Consolidate the repeated emphatic warnings ("Never...", "⚠") into a single constraints section; the current density of inline admonitions adds tokens without adding actionability.

DimensionReasoningScore

Conciseness

It assumes Claude's competence and avoids explaining known concepts, but the extensive version-history anecdotes ("Found by a dogfood", "v0.8.0 led with...") and repeated emphatic rationale are over-explanation that could be tightened beyond a minor trim.

3 / 5

Actionability

Copy-paste bash blocks, exact flags, concrete JSON payloads, and field-keyed decision branches make the guidance fully executable across the common cases (audit, experiment, dashboard, contribute, propose, schedule).

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced with validation checkpoints and feedback loops — the audit's three rules, contribute's four non-skippable steps with degrade-to-silence, and engine-refusal gates for destructive/batch operations.

5 / 5

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), yet the single ~356-line file inlines substantial per-command detail that could be split into reference files; section headers and external doc links provide structure but content that should be separate stays inline.

3 / 5

Total

16

/

20

Passed

Description

100%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 exemplary: it states concrete capabilities, gives natural trigger phrases users would actually say, explicitly covers both what and when, and occupies a distinct niche. It is concise yet comprehensive with no fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "retention stats, calibration, grader audit, n-of-1 experiments, HTML dashboard" — giving comprehensive coverage rather than just naming the domain.

5 / 5

Completeness

Explicitly answers both what (the telemetry/strategy/schedule capabilities) and when ("Use for..." with concrete trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases a user would actually say — "how am I doing", "weekly check-ins", "strategy questions", "auditing the grader", "adjusting how Engram teaches" — with good synonym coverage.

5 / 5

Distinctiveness Conflict Risk

The Engram-specific coaching niche and tightly scoped triggers make it clearly distinct from generic skills with minimal conflict risk.

5 / 5

Total

20

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

nagisanzenin/engram

Path

skills/coach/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.