Ready to supercharge your AI agents?

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

/oc-status · anthropics | DecimalAI

legalby anthropics

/oc-status

anthropics/oc-status

Source anthropics/claude-for-legal ↗License Apache-2.0

Generate weekly status-request email drafts to outside counsel across the active portfolio — markdown per matter, plus Gmail drafts when the MCP is available.

SkillScore68Maintained

Automatic

Legal & Contracts pack

Last verified 8/12/2026

What it changes

Passed 12 of 17 test cases with the skill, and 9 of 17 without it.

Without skill50%

With skill68%

Checks it passed that the model alone missed

Appends the send gate review disclaimer below the email body.
Notes Gmail integration status failure in the summary document.
Falls back to markdown file creation when Gmail draft creation fails.

and 4 more in the full report

6 fixed9 passed either way5 still failing2 broke

Pass-rate lift: +18 pp
Tokens: +176%
Agent turns: 0%
Response time: +9%

Model gemini-3.6-flashMeasured 8/12/2026v115 of 22 cases passed with skill · 17 comparable

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

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/anthropics-oc-status/SKILL.md https://app.decimal.ai/s/anthropics-oc-status/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add anthropics-oc-status, 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/anthropics-oc-status/ and pins it in .decimal/skills.lock

decimalai skills add anthropics-oc-status

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

curl -fsSL --create-dirs -o .claude/skills/anthropics-oc-status/SKILL.md https://app.decimal.ai/s/anthropics-oc-status/SKILL.md

Raw file: /s/anthropics-oc-status/SKILL.md ↗ · machine-readable summary at /s/anthropics-oc-status.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

Draft a status update request email for the 'titan-v-atlas' matter when no custom subject convention is specified in house preferences.

What was checked, without and with the skill
Checked	Without skill	With skill
Formats the fallback subject line as [Matter: [matter name]] — Weekly status update when house directive defaults are omitted.	Missed	Passed

case-10 · gemini-3.6-flash · 8/12/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md153 linessingle file

/oc-status

To run weekly, set a recurring reminder to invoke /litigation-legal:oc-status. Automated scheduling requires a scheduled-tasks integration, which is not bundled.

Load ~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml, filter per default rules (or per flags).
Load ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md → outside counsel directive style, signer defaults, budget posture.
Follow the workflow and reference below.
For each matter in scope: read matter.md + history.md, draft per-matter email.
Write markdown to ~/.claude/plugins/config/claude-for-legal/litigation-legal/oc-status/[YYYY-MM-DD]/[slug].md.
If Gmail MCP authenticated: create Gmail drafts. Else: markdown-only, note in summary.
Write ~/.claude/plugins/config/claude-for-legal/litigation-legal/oc-status/[YYYY-MM-DD]/_summary.md — what ran, what was skipped and why.

OC Status

Purpose

Writing the same status-request email to outside counsel every week across 5–15 matters is mechanical cognitive tax. The content is consistent per matter (status, decisions pending, budget check). The audience is consistent (OC lead partner). The tone is consistent (per house outside-counsel-directive style). A scheduled task drafts all of them; counsel reviews and sends.

Load context

~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml — the filtering and field source
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/matter.md — matter context (current posture, open questions)
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/history.md — recent events to inform what to ask about
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md → outside counsel directive style, signer name/email, budget posture

Filtering — which matters?

Default filter:

status != closed
outside_counsel.firm != null AND outside_counsel.lead != null
Either: last update more than 10 days old (time for something to have happened) OR has a next_deadline within 21 days

Skip matters that just had a status update in the last 10 days (no need to re-ping) and matters where outside_counsel.email is null (email addresses needed for Gmail draft; still produce markdown).

Flags:

--all → draft for every active matter regardless of recency
--slug=[slug] → draft for one matter only (ad-hoc request)

Track record

Benchmark

12 / 17

test cases passed, vs 9 / 17 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 v4 — 8/3/2026

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

anthropics / claude-for-legal

litigation-legal/skills/oc-status/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

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

/oc-status

OC Status

Purpose

Load context

Filtering — which matters?

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills