CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cc-skill-strategic-compact

Development skill from everything-claude-code

1.31x
Quality

31%

Does it follow best practices?

Impact

95%

1.31x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/cc-skill-strategic-compact/SKILL.md

The canonical home for this skill is cc-skill-strategic-compact in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

22%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 body is a stub: two content-free sentences that neither instruct nor orient, with a When-to-Use section referencing an overview that isn't there. It provides no executable guidance of any kind.

Suggestions

Replace the tautological filler with the skill's actual instructions — the concrete steps or commands for strategic context compaction (e.g. what to summarize, what to preserve, when to invoke).

Add a real 'When to Use' section listing explicit trigger conditions (e.g. session length thresholds, user requests to compact) instead of 'the workflow or actions described in the overview'.

If the workflow involves destructive/batch operations on session state, include validation checkpoints (verify no needed context is lost after compaction) to lift workflow clarity above its floor.

DimensionReasoningScore

Conciseness

The body is short with no concept over-explanation or padding, but every sentence is tautological filler ('Development skill skill.', 'applicable to execute the workflow or actions described in the overview') — the unnecessary-explanation criterion applies to the entire body rather than minor parts. Not 4/5 because none of the tokens convey information that earns its place.

3 / 5

Actionability

No concrete code, commands, or steps appear anywhere; the body only describes (tautologically) rather than instructs, matching anchor 1.

1 / 5

Workflow Clarity

There is no sequence of steps at all — the 'When to Use' section points to an overview that does not exist. The simple-skill exception cannot apply because no unambiguous single action is stated.

1 / 5

Progressive Disclosure

A section heading exists and there is no misfiled or inlined bulk content (no bundle files exist), but the body has no overview content and 'described in the overview' is a dangling pointer to a nonexistent section. Not 5 because the sections are not well-organized with real content; not 4 because the only structural element fails to orient the reader.

3 / 5

Total

8

/

20

Passed

Description

8%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 a placeholder-level label: it states neither what the skill concretely does nor when to use it, and it would be indistinguishable from any other development skill. It is far below the quality of even the bad overall examples.

Suggestions

Replace the generic label with the concrete actions this skill performs, e.g. 'Compacts Claude Code session context by summarizing conversation history…' — several specific verbs, not 'Development skill'.

Add an explicit 'Use when…' clause with natural trigger phrases a user would actually say (e.g. 'Use when the user asks to compact, summarize, or free up context in a long session').

Include distinguishing trigger terms (session compaction, context window pressure, /compact) so it does not collide with every other development skill in the bundle.

DimensionReasoningScore

Specificity

The description 'Development skill from everything-claude-code' names no concrete actions at all — it is pure abstract labeling. Anchor 2 requires at least a named domain with a generic action (e.g. 'Processes PDF files'), which this lacks.

1 / 5

Completeness

There is only an extremely vague 'what' ('Development skill') and no 'when' clause of any kind, matching anchor 2 ('vague what and no when'). Not 1 because a what-fragment is present; not 3 because the what is not clear.

2 / 5

Trigger Term Quality

No natural keywords a user would say when needing this skill; 'Development skill' is generic and 'everything-claude-code' is a source-collection label, not a trigger term.

1 / 5

Distinctiveness Conflict Risk

'Development skill' is entirely generic and would conflict with virtually any other development-related skill; nothing distinguishes it.

1 / 5

Total

5

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/cc-skill-strategic-compact/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.