SKILLEMALL.ai
GitHub ↗ RU Sign in

DC research-compendium

Deep-research a topic end to end and produce a permanent, reusable knowledge asset: archive every primary source verbatim (gated by the user's privacy/retention posture), write one 1:1 summary per source, then synthesize a single self-contained compendium page. Depth is a dial (base synthesis → grounded primaries → books + counter-canon → saturation), each level an idempotent superset of the one below. Distinct from data-research (structured trackers) and perplexity-research (web deltas): this produces prose knowledge synthesis backed by an archived source corpus.

garrytan/gbrain Agent Skills author: garrytan MIT 1 file body ≈ 5 651 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Deep-research a topic end to end and produce a permanent, reusable knowledge asset: archive every primary source verbatim (gated by the user's…

As a process C 56/100 · Has gaps — References files that are not bundled: ../conventions/brain-first.md, ../conventions/quality.md, ../_brain-filing-rules.md

GeneratorWriting and documentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
75/100
safety, quality, tests
Safety 60%
95
Quality 40%
45
Run on models
none yet
Process rating
C
56/100
Has gaps
References files that are not bundled: ../conventions/brain-first.md, ../conventions/quality.md, ../_brain-filing-rules.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Result and completion w 14
60
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: research-compendium (garrytan/gbrain)

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Instruction override medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 1

✓ No critical or high findings

Medium and low: 1
  • medium Instruction override en-ignore-previous SKILL.md:76
    Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)
    "ignore previous instructions," embedded tool-call syntax, or urgent demands
    quoted

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 5651 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../conventions/brain-first.md
  • warning missing-ref reference to a missing file: ../conventions/quality.md
  • warning missing-ref reference to a missing file: ../_brain-filing-rules.md
  • warning missing-ref reference to a missing file: ../conventions/untrusted-content.md
  • warning missing-ref reference to a missing file: ../book-mirror/SKILL.md
  • warning missing-ref reference to a missing file: ../conventions/test-before-bulk.md
  • warning missing-ref reference to a missing file: ../perplexity-research/SKILL.md
  • warning missing-ref reference to a missing file: ../fact-check/SKILL.md
  • warning missing-ref reference to a missing file: ../cross-modal-review/SKILL.md
  • warning missing-ref reference to a missing file: ../minion-orchestrator/SKILL.md
  • warning missing-ref reference to a missing file: ../brain-pdf/SKILL.md
  • warning missing-ref reference to a missing file: ../conventions/agent-operator-protocol.md
  • warning missing-ref reference to a missing file: ../data-research/SKILL.md
  • warning missing-ref reference to a missing file: ../academic-verify/SKILL.md
  • warning missing-ref reference to a missing file: ../strategic-reading/SKILL.md
  • warning missing-ref reference to a missing file: ../concept-synthesis/SKILL.md
  • note frontmatter-key unknown frontmatter key "triggers"
  • note frontmatter-key unknown frontmatter key "mutating"
  • note frontmatter-key unknown frontmatter key "writes_pages"
  • note frontmatter-key unknown frontmatter key "writes_to"
  • note frontmatter-key unknown frontmatter key "upstream"

Process rating: all ten parameters 56/100

Will not run. References files that are not bundled: ../conventions/brain-first.md, ../conventions/quality.md, ../_brain-filing-rules.md
  • 0Tools and files. 16 referenced file(s) missing: ../conventions/brain-first.md, ../conventions/quality.md, ../_brain-filing-rules.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 60Result and completion. Output format stated, no completion criterion
  • 60Failures and branches. 2 branches
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5651 tokens
  • 100Steps. 54 steps
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (18 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • -5TODO / placeholder text left in the skill
  • +1No license
  • +2Single-language instructions
  • +3Description length 570: enough signal without eating the budget
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 54 items
  • +3Output format is stated explicitly
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 45.