CtrlK
BlogDocsLog inGet started
Tessl Logo

strategic-compact

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. Use when a session is approaching a context limit and a task phase is a natural place to compact.

66

Quality

78%

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/strategic-compact/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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, largely actionable body: concrete hook setup, configuration, decision tables, and version-specific caveats about what survives compaction. The main gap is that the referenced `suggest-compact.js` script is not shipped, so the setup instructions cannot actually be executed end-to-end, and a couple of sections carry padding.

Suggestions

Ship `suggest-compact.js` in a `scripts/` directory (and update the hook paths to a relative reference) so the copy-paste hook setup actually works instead of pointing at a file the reader must write themselves.

Trim the 'Why Strategic Compaction?' motivation section and the nested parentheticals in 'How It Works' — the thresholds and signals can be stated as a short table, and the todo-tools caveat can be cut to its actionable core ('write the plan to a file; the task list may not exist').

Resolve the dangling references: link the `continuous-learning` skill and the longform guide to concrete targets, or drop the 'Related' section, since neither resolves from this skill's bundle.

DimensionReasoningScore

Conciseness

Mostly dense, non-obvious content (window-scaled thresholds, env vars, what-survives table, version-specific todo-tools caveat), but the "Why Strategic Compaction?" section is motivational padding and the 13-line blockquote plus heavily nested parentheticals in "How It Works" could be tightened — efficient with minor over-explanation, not anchor 5.

4 / 5

Actionability

Copy-paste hook JSON, concrete env vars with defaults, a phase-transition decision table, and a worked `/compact Focus on implementing auth middleware next` example make the guidance mostly executable, but the entire mechanism depends on `suggest-compact.js`, whose behavior is described yet whose code is not shipped in the bundle, leaving a gap that keeps it below anchor 5.

4 / 5

Workflow Clarity

The Compaction Decision Guide gives an explicit per-phase checkpoint table (Compact? / Why) and the write-before-compacting rule is stated repeatedly; compaction is not a destructive/batch operation so no validation cap applies. The setup → configure → respond sequence is implied by section order rather than given as an explicit ordered workflow, which keeps it at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

Well-organized single-file structure with one-level-deep references only and appropriately inlined decision tables, but at ~120 lines it exceeds the under-50-line exception, and it references a script (`suggest-compact.js`) and related skills (`continuous-learning`) that are not present in the bundle, so minor organization gaps remain.

4 / 5

Total

16

/

20

Passed

Description

82%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: third-person voice, explicit what-and-when structure, and concrete trigger conditions for a well-defined niche. Its only weakness is that it stays at one action's level of abstraction and does not preview the skill's more specific capabilities.

DimensionReasoningScore

Specificity

"Suggests manual context compaction at logical intervals" names the domain and one concrete action, but does not list several specific capabilities (no mention of the hook, thresholds, or signals the body delivers), matching the 'names domain and 1-2 concrete actions' anchor rather than the 'lists several specific actions' anchor.

3 / 5

Completeness

It explicitly answers both what ("Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction") and when ("Use when a session is approaching a context limit and a task phase is a natural place to compact") with concrete trigger conditions, matching the anchor-5 example pattern; it is not anchor 4 because the when-clause is specific, not merely present.

5 / 5

Trigger Term Quality

Natural phrases like "a session is approaching a context limit", "task phase", and "auto-compaction" give good keyword coverage for this niche, though common variations users might say ("running out of context", "long session", "/compact") are missing, so it fits anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The combined trigger (context-limit approach plus phase boundary) carves a clear niche distinct from memory/persistence or general session-management skills, with minimal risk of firing for the wrong skill.

5 / 5

Total

17

/

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
affaan-m/ECC
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.