Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Panel review · fallow-rs | DecimalAI

productivityby fallow-rs

Panel review

fallow-rs/panel-review

Source fallow-rs/fallow ↗License MIT

Review a Fallow design, plan, workflow, CLI surface, documentation architecture, or user experience with representative end-user and domain-expert perspectives before implementation.

SkillScore52Maintained

Automatic

Product Management pack

Last verified 9/28/2026

What it changes

Passed 8 of 16 test cases with the skill, and 5 of 16 without it.

Without skill32%

With skill52%

Checks it passed that the model alone missed

Categorizes missing cache hit telemetry under Fix now in `.plans/llm-cache.md`.
Categorizes the unverified security claim as No action in `.plans/auth-migration.md`.
Verifies the token redacting claim against `logger.go` source code before accepting it.

and 7 more in the full report

6 fixed7 passed either way11 still failing1 broke

Pass-rate lift: +20 pp
Tokens: -17%
Agent turns: 0%
Response time: -13%

Model gemini-3.6-flashMeasured 9/28/2026v2 · latest is v413 of 25 cases passed with skill · 16 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.6-flash on 10/4/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/fallow-rs-panel-review/SKILL.md https://app.decimal.ai/s/fallow-rs-panel-review/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add fallow-rs-panel-review, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/fallow-rs-panel-review/ and pins it in .decimal/skills.lock

decimalai skills add fallow-rs-panel-review

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/fallow-rs-panel-review/SKILL.md https://app.decimal.ai/s/fallow-rs-panel-review/SKILL.md

Raw file: /s/fallow-rs-panel-review/SKILL.md ↗ · machine-readable summary at /s/fallow-rs-panel-review.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

We are reviewing `.plans/sdk-v3.md` for our Python SDK. Compatibility team noted that removing `client.connect()` without a deprecation warning breaks existing v2 integrations (must fix before shipping v3). Security team found an unhandled TLS certificate validation exception in current v2 code. Record these in `.plans/sdk-v3.md`.

What was checked, without and with the skill
Checked	Without skill	With skill
Categorizes adding deprecation warnings prior to v3 release under Fix before change in `.plans/sdk-v3.md`.	Missed	Passed
Categorizes fixing the TLS certificate validation exception under Fix now in `.plans/sdk-v3.md`.	Missed	Passed

case-18 · gemini-3.6-flash · 9/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md25 linessingle file

Panel review

Read the controlling plan or specification first.
Build one evidence package from current source, live behavior, and relevant public contracts.
Select representative users plus specialists for accessibility, security, privacy, compatibility, operations, or agent runtimes as applicable.
Ask reviewers for concrete blockers, concerns, follow-ups, and no-action decisions.
Verify load-bearing claims against source before accepting them.
Filter the findings first. Drop style preferences and "a different design would also work" unless the reviewer shows a concrete problem. Trace a call site before you accept a bug claim. Put each dropped finding under No action with one reason.
Synthesize consensus under:
- Fix before change
- Fix now
- Follow-up
- No action
Record approved decisions in the active .plans/<task>.md.

Do not expose private source text or internal review labels in public output. Panel feedback is evidence, not authority over tested contracts.

Track record

Benchmark

8 / 16

test cases passed, vs 5 / 16 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/30/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

fallow-rs / fallow

.agents/skills/panel-review/SKILL.md

View on GitHub ↗

License MITImported 9/30/2026Version v4

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Panel review

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills