CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

abstraction

Shape a complex idea, workflow, design, or report on work into the smallest complete surface a person needs for the next judgment. Use when summarizing, reporting on, or explaining complex work to someone who must judge or act on it, when proposing a change that is easier to judge shown than described, or when an explanation obscures its point or makes the user carry unnecessary complexity.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/abstraction/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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-organized, self-contained instructional skill with a concrete tactical core (the short pass, comparison-table guidance, preserve-list, and failure-mode checklist). Its main cost is redundancy: the governing principle is restated across at least five sections, and a compact worked example would raise actionability without adding length.

Suggestions

Consolidate the repeated statement of the core principle — the intro, 'The test' blockquote, 'Reveal progressively', and 'Stop' all restate 'show only what the judgment depends on'; stating it once prominently could cut roughly a quarter of the body.

Add one compact worked example (a before/after of a short report or restatement) to make the guidance concrete; the skill itself argues for exactly this.

Merge 'With dialectic' into a brief note near the top, since its guidance substantially repeats the pairing already stated in the intro.

DimensionReasoningScore

Conciseness

The body does not explain concepts Claude already knows, but its single core principle is restated several times — the intro ('Show the person the part of a model they need now'), 'The test' blockquote, 'Reveal progressively', 'A short pass', and 'Stop' all restate 'show only what the judgment depends on'. This matches anchor 3 (mostly efficient but could be tightened) rather than anchor 2, since the prose is dense rather than padded.

3 / 5

Actionability

For an instruction-only skill the guidance is concrete: 'a comparison table with the dimensions they care about as rows', 'code, a before and after, or a small diagram', 'reader / author, user / system... paired viewpoint', 'put it after the evidence it depends on, at the end', plus a 6-step 'short pass'. It falls short of anchor 5 because there is no worked example of a good versus bad report or restatement, which this skill's own advice would benefit from.

4 / 5

Workflow Clarity

'A short pass' is a clear 6-step sequence with embedded checkpoints (step 5: 'Check that separate owners have not been collapsed and deferred decisions have not been presented as settled'), the 'Watch for' list functions as a failure-mode checklist, and 'Stop' gives explicit exit criteria. This matches anchor 4; it does not reach 5 because the checks are self-review heuristics rather than explicit validate-and-retry feedback loops, and the workflow is embedded in substantial surrounding prose.

4 / 5

Progressive Disclosure

The skill is a single self-contained file with clear, well-ordered section headers and no external references — none are needed, and no bundle files exist, so nothing is buried or nested. It matches anchor 4's 'good structure; most content appropriately placed; minor organization gaps'; at ~135 lines it exceeds the under-50-line simple-skill exception that would allow a 5 on organization alone.

4 / 5

Total

15

/

20

Passed

Description

70%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 well-structured description with an explicit, multi-scenario 'Use when' clause, third-person voice, and natural trigger terms. Its main weakness is that the core capability is expressed abstractly ('the smallest complete surface'), which lowers the concreteness of the 'what' without adding vagueness to the 'when'.

Suggestions

State the core action in plainer operational terms — e.g., 'Condense complex work into the summary, diff, diagram, or decision frame the reader needs to judge it' — so the 'what' is concrete rather than expressed as 'the smallest complete surface'.

Add a few natural trigger synonyms users would say, such as 'simplify', 'condense', or 'give me the short version', to broaden trigger-term coverage.

Tighten the 'when' clause by trimming the third scenario ('when an explanation obscures its point or makes the user carry unnecessary complexity'), which partially restates the first two.

DimensionReasoningScore

Specificity

The description states its domain and several actions ('summarizing, reporting on, or explaining complex work', 'proposing a change'), but the core capability is phrased abstractly as shaping something 'into the smallest complete surface a person needs for the next judgment' — a conceptual rather than concrete operation. It sits between anchor 3 (1-2 concrete actions, not comprehensive) and anchor 4 (several specific actions); the abstract framing of the actions keeps it at 3 rather than 4.

3 / 5

Completeness

Both parts are explicit: the 'what' ('Shape a complex idea, workflow, design, or report on work into the smallest complete surface...') and a multi-scenario 'Use when' clause with concrete trigger situations. It does not clearly reach anchor 5 because the 'what' relies on the abstract 'smallest complete surface' phrasing rather than plainly stating what is done, landing it between anchors 4 and 5.

4 / 5

Trigger Term Quality

Includes natural phrases a user would actually say — 'summarizing', 'reporting on', 'explaining complex work', 'proposing a change', 'an explanation obscures its point' — giving good keyword coverage. A few natural terms are missing (e.g., simplify, condense, TL;DR, executive summary), so it does not reach the comprehensive synonym coverage of anchor 5, but it clearly exceeds anchor 3's 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

It carves a mostly distinct niche — presenting complex work so someone can judge or act on it — and explicitly differentiates the companion skill ('It pairs with `dialectic`'). There is minor overlap risk with generic summarization or communication skills, matching anchor 4 rather than the minimal-conflict clarity of anchor 5.

4 / 5

Total

15

/

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

EpicenterHQ/epicenter

Path

.agents/skills/abstraction/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.