pd-pipeline-review
Skill0 starsChanged 32 days agoMITView on GitHub
Pipeline review for managers and owners in three modes: review (by rep and stage, stuck and risky deals), forecast (stage probability vs real activity, slipping close dates), digest (short weekly business summary). Use for pipeline review, forecast check, weekly digest or team performance questions.
In this repository19 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- pd-accessSkill
- pd-account-healthSkill
- pd-advisorSkill
- pd-askSkill
- pd-coreSkill
- pd-crm-architectSkill
- pd-data-hygieneSkill
- pd-follow-upSkill
- pd-icp-discoverySkill
- pd-industrySkill
- pd-lead-qualifierSkill
- pd-morning-briefSkill
- pd-playbook-minerSkill
- pd-premortemSkill
- pd-setupSkill
- pd-thread-mapSkill
- pd-win-backSkill
- pd-win-lossSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Follow pd-core rules (load pd-core if not loaded).
- Very specific: line 26
Run pd-core/scripts/pd_digest.py on the result (save the result to a file first when a shell is available) with --group stage, then --group …
- Distinctive: line 67
Never present the evidence-based forecast as certain.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
pd-pipeline-review
Follow pd-core rules (load pd-core if not loaded).
Team scope: if .pipedrive/access.json is missing or shows partial coverage, run pd-access checks 1 and 2 first and state the coverage in the first line.
Requires: Pipedrive (manager/admin visibility for team results)
Optional: Slack/Teams (post digest, opt-in), Google Docs (report)
Fallback: chat + file pipedrive-out/pd-pipeline-review/<date>.md
Mode
Pick from the request: "review" (default), "forecast", "digest". Scope: pipeline (ask if more than one and not named), owner (all visible by default), period (this month/quarter for forecast).
Steps
- Context from cache. Note if the user cannot see other reps' deals (pd-setup records this).
- Fetch:
getDeals pipeline_id=<id> status=open limit=500 include_fields=[next_activity_id,undone_activities_count,last_activity_id]. 500+ open deals: split by owner; in Claude Code use one subagent per owner, each returning at most 10 lines. - Run
pd-core/scripts/pd_digest.pyon the result (save the result to a file first when a shell is available) with--group stage, then--group owner. - Mode specifics:
- review: stuck = in the same stage longer than 2x the median for that stage (use
stage_change_timeif present, elseupdate_time). List top 10 risky deals. Pull notes (getNotes deal_id limit=3) only for the top 5. - forecast: for deals with close date in the period, compare stage probability vs evidence: no activity in 14+ days, close date already pushed (notes or
expected_close_datein the past), no next step, single contact. Produce "committed" (strong evidence), "at risk", "unlikely". Sum per bucket per currency. - digest: won/lost this week:
getDeals status=won updated_since=<monday>andstatus=lost; new dealsgetDeals sort_by=add_time sort_direction=desc updated_since=<monday>. One-paragraph pulse plus 3 actions.
- review: stuck = in the same stage longer than 2x the median for that stage (use
- Compare with the last report file if present: deltas only (value change, new risks, resolved risks).
- Route output (config). Slack/Teams only when opted in.
Output (review)
Pipeline <name> | <n> open | <value per currency> | vs last week: <+/->
By stage: <stage n value> ...
By owner: <owner n value stale no_next> ...
Stuck / risky (top 10):
- <id> | <deal> | <stage> | <value> | <owner> | <reason>
Coaching points:
- <owner>: <pattern, one line>
Actions this week:
1. ...Output (forecast)
Period <month> | pipeline <name>
Committed: <value> (<n>) | At risk: <value> (<n>) | Unlikely: <value> (<n>)
Weighted by Pipedrive stage: <value>. Evidence-based: <value>. Gap: <value>.
At risk:
- <id> | <deal> | <value> | <owner> | <evidence>Output (digest)
Week <n>: won <value> (<n>), lost <value> (<n>), new <n> deals.
<2-3 sentence pulse>
Watch: <top 3 risks>
Do: <3 actions>Never present the evidence-based forecast as certain. State the rules used in one line.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

