CtrlK
BlogDocsLog inGet started
Tessl Logo

latent-briefing

This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.

60

Quality

69%

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 ./skills/latent-briefing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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, appropriately progressive body that delegates deep math to a real reference file and embeds evaluation checkpoints into its guidance. Its main weakness is actionability: the compaction procedure stays at the pseudocode/conceptual level, so a reader understands the idea but cannot execute the core operation from the body alone.

Suggestions

Add a minimal executable sketch of the compaction step (e.g., the per-position scoring and masking loop in the reference's conceptual block) so the core operation is reproducible, not just described.

De-duplicate the three modifications between 'Core Concepts' and 'Three Inference-Time Modifications' — keep the brief list in Core Concepts and point to the detailed section instead of restating.

Consider dropping or trimming the dated metadata footer (Created/Last Updated/Version) since it adds time-sensitive bulk that does not guide usage.

DimensionReasoningScore

Conciseness

The body is efficient and mostly assumes Claude's competence, explaining the specialized technique (AM, KV compaction) without padding generic ML concepts. Minor trim opportunities exist: the three modifications appear both in 'Core Concepts' and again expanded in 'Three Inference-Time Modifications', and the dated metadata footer adds bulk. Not a 5 because of that overlap; not a 3 because the duplication is minor and most content earns its place.

4 / 5

Actionability

Concrete guidance is present — the MAD threshold formula ('median + tau * MAD'), a numbered set of modifications, a decision-framework table, and a call-sequence example — but the core compaction procedure is conveyed as pseudocode ('compact KV(T2) using the task prompt for B') with the actual implementation deferred to the reference and external papers. Not a 4 because the executable core is incomplete; not a 2 because the guidance is specific and structural rather than vague hints.

3 / 5

Workflow Clarity

A clear decision sequence is provided via the decision-framework table and 'Practical Guidance', with evaluation treated as an explicit checkpoint ('Co-design compaction with evaluation', 'Tune on validation data, not anecdotes', 'Measure end-to-end latency'). Not a 5 because there is no full validate→fix→retry feedback loop; not a 3 because evaluation checkpoints are present and the selection sequence is clear. The destructive/batch cap does not apply to this advisory skill.

4 / 5

Progressive Disclosure

Clear overview structure (When to Activate, Core Concepts, Detailed Topics, Examples, Gotchas, Integration, References) with a well-signaled one-level-deep reference to ./references/attention-matching-formulation.md — verified to exist — each carrying a 'Read when:' navigation cue. The deep AM formulation is appropriately split into the reference rather than inlined. Not a 4 because references are clearly signaled and content is appropriately split with easy navigation.

5 / 5

Total

16

/

20

Passed

Description

67%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 an excellent trigger list with strong distinctiveness but is one-sided: it tells Claude exhaustively when to activate yet never states what the skill actually does. Adding a concise action clause would lift specificity and completeness.

Suggestions

Lead with a brief action statement of what the skill does, e.g. 'Compacts the orchestrator trajectory into the worker model's KV cache via Attention Matching so workers receive task-relevant latent state without replaying full text.'

Keep the strong trigger list but pair it with the 'what' so completeness covers both halves explicitly.

No change needed for trigger terms or distinctiveness — both are already strong.

DimensionReasoningScore

Specificity

The description names the domain ('KV cache compaction for multi-agent', 'share memory between agents', 'latent briefing') but states no concrete actions the skill performs — it is trigger-only with no 'does X' verb. Not a 1 because the domain is specific rather than vague; not a 3 because there is no concrete action listed, only topical triggers.

2 / 5

Completeness

The 'when' is extremely explicit ('This skill should be used when the user asks to...') but the 'what' is only implied through the trigger topics, never stated as an action. Not a 2 because the 'when' guidance is rich and specific rather than a bare 'Use when working with documents'; not a 4 because there is no explicit statement of what the skill does.

3 / 5

Trigger Term Quality

Comprehensive natural trigger phrases with synonyms and variations — 'share memory between agents', 'reduce worker tokens', 'cross-agent memory without summarization', 'token explosion in hierarchical agents', 'Attention Matching compaction'. These are the terms a user needing this niche technique would actually say; coverage is broad rather than a few generic keywords, so it clears the 4 anchor.

5 / 5

Distinctiveness Conflict Risk

Triggers are highly niche and specialized ('KV cache compaction for multi-agent', 'latent briefing', 'Attention Matching compaction', 'recursive language models with workers'), giving a clear niche with minimal overlap risk against general skills. Not a 4 because nothing here would plausibly fire a different skill.

5 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
muratcankoylan/Agent-Skills-for-Context-Engineering
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.