CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deconfliction-template

Deconfliction plan generator: distinguish authorized engagement activity from real incidents.

Quality

74%

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 ./packages/decepticon/decepticon/skills/standard/soundwave/deconfliction-template/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-structured, instruction-only skill: a concrete five-step workflow with field-level rules and a complete schema table, plus an explicit validation step, all with zero padding. The only notable gaps are the missing error-recovery loop and unspecified validation mechanism, plus the absence of a worked example of the output document.

DimensionReasoningScore

Conciseness

The ~33-line body is lean and assumes domain competence (no explanation of what deconfliction, RoE, CONOPS, or a SOC is); every section earns its place: a two-line "When to Use", five terse workflow steps with specific field names, and a compact schema table. Only trivial repetition exists (validation against `DeconflictionPlan` mentioned in step 5 and the schema section), which serves as useful reinforcement rather than padding — matching anchor 5 ("Lean and efficient; assumes Claude's competence; every token earns its place").

5 / 5

Actionability

For an instruction-only skill the guidance is highly concrete: exact file paths ("plan/roe.json", "plan/deconfliction.json"), per-field rules ("Each entry needs `type` and `value`; put context in `description`"), and a complete field/type/required schema table. It stops short of anchor 5 because there is no worked example of a filled deconfliction.json and the validation step ("Validate `plan/deconfliction.json` against `DeconflictionPlan`") gives no command or mechanism, leaving minor gaps.

4 / 5

Workflow Clarity

The five steps are clearly sequenced (preserve existing decisions → record identifiers → set notification procedure → set deconfliction code → validate) and step 5 is an explicit validation checkpoint, matching anchor 4. It is not anchor 5 because there is no error-recovery feedback loop (what to do when validation fails) and the validation mechanism itself is unspecified; it exceeds anchor 3, which requires missing or implicit checkpoints.

4 / 5

Progressive Disclosure

No bundle files (references/, scripts/, assets/) exist and none are referenced, and the skill is under 50 lines with well-organized sections ("When to Use", "Workflow", "Document schema"); the short schema table is core operational content that appropriately lives inline. Per the rubric's simple-skill note, this earns anchor 5 ("Clear overview with well-signaled... content appropriately split; easy navigation") on section organization alone.

5 / 5

Total

18

/

20

Passed

Description

53%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 states a clear, domain-specific capability with concrete framing, but it omits any explicit 'when to use' trigger guidance and under-represents the natural trigger terms (SOC notification, red-team identifiers) that appear only in the metadata. It is distinctive within the red-team planning niche. Adding a 'Use when...' clause with concrete trigger phrases would address the two lowest dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when creating or revising a deconfliction plan, defining red-team identifiers, or configuring SOC notification for an engagement.", to raise completeness from 3.

Include natural trigger phrases users would actually say — "SOC notification", "rules of engagement", "red-team engagement", "notify the SOC" — to broaden keyword coverage beyond "deconfliction plan" and "real incidents".

Enumerate the concrete actions the skill performs (e.g., "records approved identifiers, sets the SOC notification procedure, and validates plan/deconfliction.json") for fuller capability coverage than the single distinguishing action.

DimensionReasoningScore

Specificity

"Deconfliction plan generator: distinguish authorized engagement activity from real incidents" names the domain plus roughly two concrete actions (generate deconfliction plans; distinguish authorized activity from incidents), but coverage is not comprehensive — it omits identifiers, SOC notification, and validation actions. It is more concrete than anchor 2 ("Names the domain but actions are minimal or generic") because the distinguishing action is specific, but does not list the several actions required for anchor 4.

3 / 5

Completeness

The "what" is clear (generates deconfliction plans; distinguishes authorized engagement activity from real incidents), but the description contains no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. This matches anchor 3 ("Has a clear 'what' but 'when' is missing or only weakly implied"); it cannot be 4 without an explicit when-clause, and is above anchor 2 because the what is concrete rather than vague.

3 / 5

Trigger Term Quality

The description includes some relevant natural keywords — "deconfliction plan", "engagement activity", "real incidents" — that a user in this domain would say, but misses common variations and synonyms such as "SOC notification", "red-team identifiers", "rules of engagement", or "notify the SOC". This matches anchor 3 ("Some relevant keywords but missing common variations or synonyms") rather than anchor 4's good keyword coverage.

3 / 5

Distinctiveness Conflict Risk

"Deconfliction plan generator" carves out a specialized niche (red-team engagement deconfliction) that is unlikely to trigger unrelated skills, fitting anchor 4 ("Mostly distinct; minor overlap risk with closely related skills"). It is not a 5 because the phrase "real incidents" and the absence of distinct trigger phrases leave minor overlap risk with incident-triage and SOC-response skills; it is clearly above anchor 3, which implies broader overlap.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/soundwave/deconfliction-template/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.