CtrlK
BlogDocsLog inGet started
Tessl Logo

distilly

Build and use evidence-grounded local person profiles with Distilly's exact five-tool workflow. Use when a user asks to research, ingest, distill, update, correct, retrieve, or recall a real or fictional person's profile, voice, boundaries, or evidence.

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is distilly in titanwings/distilly

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 skill body is a tightly written, executable specification of a fragile multi-step workflow with concrete templates, explicit validation/feedback loops, and a correctly structured single reference file. Its only minor weakness is some procedural repetition that could be trimmed for token efficiency.

Suggestions

Consolidate the repeated requestId/wireVersion shape guidance and the create-vs-existing selector rules into one canonical section to reduce restatement across 'Establish the task' and 'Ingest and dispatch the result'.

The 32-material batching and byte-limit rules appear in both SKILL.md and source-materials.md; keep the canonical limit in one place and reference it from the other to avoid drift.

A short inline checklist summarizing the resolve->ingest->brief->commit->verify happy path at the top would let Claude skip the prose on routine runs and fall back to detail only on failures.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence (no explaining what profiles or wire protocols are), with every section adding workflow-specific detail Claude would not already know. A few procedural clauses are restated across sections and could be tightened slightly.

4 / 5

Actionability

Provides fully executable, copy-paste-ready JSON templates for resolve, profile, commit, and correct calls, plus exact field mappings from briefing to commit fields, covering the common cases precisely.

5 / 5

Workflow Clarity

The full sequence (gate runtime, establish task, start from supplied sources, gather, ingest, brief, commit, finish, corrections) is clearly ordered with explicit validation checkpoints, lease-renew/release handling, stale-failure retry loops, and explicit stop conditions.

5 / 5

Progressive Disclosure

SKILL.md is an overview with two well-signaled, one-level-deep references to references/source-materials.md (a real bundle file), with detail appropriately split out rather than inlined as a monolith.

5 / 5

Total

19

/

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 concise, third-person, and clearly states both capability and trigger conditions with a strong, specific verb set. It matches the top anchors across all four dimensions without verbosity or over-claiming.

DimensionReasoningScore

Specificity

Names the domain ('evidence-grounded local person profiles') and lists multiple concrete actions (research, ingest, distill, update, correct, retrieve, recall) tied to a defined five-tool workflow, giving comprehensive coverage of capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (build and use evidence-grounded profiles via the five-tool workflow) and 'when' ('Use when a user asks to research, ingest, distill, ...'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes comprehensive natural trigger verbs a user would actually say ('research, ingest, distill, update, correct, retrieve, or recall') plus concrete object terms ('profile, voice, boundaries, or evidence'), covering synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Targets a clear, narrow niche (Distilly local person profiles) with distinct, specific trigger verbs, making conflict with unrelated skills minimal.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
titanwings/distilly
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.