CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mirror

Read the author's last 90 days of daily notes, the notes and call transcripts they link to, and Readwise highlights, then reflect back the questions they keep circling as clusters with evidence. Saves each run's clusters so returning themes stand out and flags unpublished drafts that match. Use when the author asks what to write about, wants to see what they've been thinking about, or starts a writing session without a topic.

Quality

94%

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

86%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-crafted, instruction-only skill body: every step is concrete and executable, safety posture (untrusted text, speaker attribution, never overwriting history) is explicit, and structure is clean. The only flaws are a small duplicated framing between intro and non-goals section and a couple of unhandled edge cases in the workflow.

Suggestions

Trim the duplicated stance statement in the intro ('The mirror doesn't score ideas or pick one. It reflects back the clusters and lets the author choose.') since the 'What the mirror doesn't do' section already covers it.

Add a brief edge-case branch to the procedure: what to report when the 90-day window contains no daily notes (or no qualifying clusters), so the run degrades gracefully instead of leaving the behavior implicit.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no explanations of concepts Claude already knows — but the opening paragraph ("The mirror doesn't score ideas or pick one. It reflects back the clusters and lets the author choose.") restates what the closing "What the mirror doesn't do" section already covers, a minor redundancy that could be trimmed.

4 / 5

Actionability

Guidance is fully concrete for an instruction-only skill: a copy-paste Readwise command with an explicit pagination stop condition, exact paths (Daily/YYYY-MM-DD.md, Mirror/history/), a quantified cluster bar (3+ pieces of evidence from 2+ distinct sources), and a complete report template with attributed, dated evidence lines.

5 / 5

Workflow Clarity

The seven numbered steps are clearly sequenced with fallback branches (unlabeled speakers treated as context, Readwise export falling back to the CLI) and a never-overwrite guard on the one write operation. It falls short of anchor 5 only for minor validation gaps: no handling for an empty window (no daily notes found) and no verification step after saving the history file.

4 / 5

Progressive Disclosure

There are no bundle files, and none are needed: the ~110-line body is one coherent procedure with clean sections (Setup table, Untrusted text, seven numbered steps, explicit non-goals). Nothing that belongs in a separate file is inlined, and navigation is easy, satisfying the well-organized single-file case.

5 / 5

Total

18

/

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.

An exemplary description: third person, concrete actions covering the full pipeline, an explicit trigger clause with natural user phrasings, and a distinctive niche. Every clause carries information with no padding or over-claims.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Read the author's last 90 days of daily notes, the notes and call transcripts they link to, and Readwise highlights", "reflect back the questions they keep circling as clusters with evidence", "Saves each run's clusters", "flags unpublished drafts" — comprehensively covering the skill's behavior with no vague filler, matching the anchor-5 example's coverage.

5 / 5

Completeness

Both halves are explicit: a clear "what" (read notes/transcripts/highlights, cluster with evidence, save history, flag drafts) and an explicit "Use when..." clause with three concrete trigger phrases, mirroring the anchor-5 example structure.

5 / 5

Trigger Term Quality

The trigger clause gives three natural user phrasings ("asks what to write about", "wants to see what they've been thinking about", "starts a writing session without a topic") plus matching domain keywords (daily notes, Readwise, transcripts, drafts, themes). Coverage of natural terms and synonyms is essentially complete for this niche, so it fits anchor 5 rather than anchor 4's "a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

It carves a clear niche — reflecting the author's own notes back as evidence-backed question clusters for writing sessions — with triggers unlikely to fire for unrelated skills; no meaningful overlap with generic note or writing helpers.

5 / 5

Total

20

/

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

shortrib-labs/content-loop

Path

plugins/mirror/skills/mirror/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.