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.

73

Quality

90%

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

88%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 highly actionable, well-sequenced workflow with concrete templates and strong validation feedback loops. The main gaps are minor repetition across sections and detail that could be pushed further into the reference file.

Suggestions

Consolidate the repeated wireVersion/requestId and subject.kind rules into one stated-once section to reduce token redundancy.

Move the detailed ingest field-shape and source-portfolio guidance (currently restated in SKILL.md) more fully into references/source-materials.md so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

Dense and procedural with no basic-concept padding and every line earning its place, but the wireVersion/requestId and subject.kind rules are restated across sections, adding avoidable repetition.

4 / 5

Actionability

Provides exact, copy-paste-ready JSON templates for resolve, profile/status/prompt, and commit, plus concrete field mappings and explicit dispatch branches covering the common cases.

5 / 5

Workflow Clarity

Clear sequence (establish → gather → ingest → brief → commit → finish) with explicit validation checkpoints, stale-failure feedback loops (discard → re-read → re-brief → regenerate), and enumerated stop conditions for a batch operation.

5 / 5

Progressive Disclosure

Well-sectioned overview with a clearly signaled one-level-deep reference (source-materials.md), though substantial operational detail remains inlined in SKILL.md rather than split out.

4 / 5

Total

18

/

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.

A strong description that concretely names the capability and provides an explicit, trigger-rich 'Use when' clause. Its only weakness is leaning on product jargon ('ingest', 'distill') that users may not naturally voice.

DimensionReasoningScore

Specificity

Names the domain and lists multiple concrete actions (build, use, research, ingest, distill, update, correct, retrieve, recall), giving comprehensive coverage of the workflow's operations.

5 / 5

Completeness

Explicitly states both what ('Build and use evidence-grounded local person profiles with Distilly's exact five-tool workflow') and when ('Use when a user asks to research, ingest, distill...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user terms (research, recall, profile, voice, boundaries, evidence) with synonyms (retrieve/recall), but 'ingest' and 'distill' are product jargon users would rarely say naturally.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Distilly person-profile memory) with distinct, specific triggers and minimal overlap with other skills.

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.

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.