retainer-reporting
Skill1 starsChanged 3 months agoMITView on GitHub
Assemble the monthly client performance report that justifies a retainer — leads by source, cost per lead, work shipped, next month's plan — with honest availability gates on every metric (no access = flagged gap, never an invented number). Triggers - "monthly report", "retainer report", "client performance report", "<CLIENT> monthly". NOT for weekly check-in agendas — use weekly-client-checkin.
In this repository47 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- access-transfer-trackerSkill
- ai-3d-generatorSkill
- ai-asset-generatorSkill
- ai-demo-builderSkill
- apple-grade-designSkill
- brand-guide-builderSkill
- client-onboardingSkill
- cold-email-campaignSkill
- cold-emailSkill
- company-teardownSkill
- competitive-ads-extractorSkill
- content-calendarSkill
- content-repurposerSkill
- content-research-writerSkill
- content-strategySkill
- daily-briefSkill
- discovery-call-prepSkill
- email-composerSkill
- follow-up-nurtureSkill
- gbp-local-seoSkill
- hormozi-100m-leadsSkill
- interactive-website-builderSkill
- invoice-trackerSkill
- lead-flow-verifierSkill
- lead-scraperSkill
- mcp-integrationSkill
- meeting-listenerSkill
- post-purchase-email-seriesSkill
- productization-journalSkill
- proposal-generatorSkill
- prospect-workupSkill
- regulated-copy-complianceSkill
- review-managerSkill
- scroll-demo-builderSkill
- seo-auditSkill
- site-launch-cutoverSkill
- site-qa-checklistSkill
- social-media-auditorSkill
- social-media-managerSkill
- social-video-producerSkill
- stylized-3d-worldbuildingSkill
- video-analyzerSkill
- web-researchSkill
- website-builderSkill
- weekly-client-checkinSkill
- welcome-email-seriesSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
Cost per lead: only computable when an ad platform is accessible AND spend is known.
- Distinctive: line 93
Write-back: log an activity note on the client's workspace record (date, type: deliverable, summary + report path) and update the matching …
- Distinctive: line 98
If the report (or next month's plan) mentions or implies a regulated topic for a client with a compliance ruleset — promotional financing …
≈ “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
Retainer Reporting
Monthly proof-of-value report. A retainer renews on demonstrated results, and this
document is where those results either land or visibly don't. For a client with multiple
business lines, default to one combined report with a section per line — confirm with the
founder on first run and record the choice in decisions/log.md.
Iron rule — no fabricated metrics, EVER
A report with honest gaps beats a report with invented numbers. Every figure must trace to a data pull you actually ran this session. If a source is inaccessible, the report says so plainly ("Ad-platform reporting comes online once account access transfers — requested via the access matrix") — never estimate, extrapolate, or reuse last month's figure as this month's.
Step 1 — Inputs inventory with availability gates
For each source, VERIFY access by pulling real data before you rely on it. "Connected" or
"credentials exist" is not access — the gate is a real record returned this session. The
client's live access state lives in clients/<slug>/access/access-matrix.md
(see access-transfer-tracker).
| Source | What it feeds |
| Analytics (GA4 / Search Console or equivalent) | Traffic, top pages, search queries |
| Search ads platform | Spend, cost per lead |
| Social ads platform | Spend, cost per lead |
| Business-profile insights (Google/maps listing) | Calls, direction requests, profile views |
| Call/lead log | Leads by source — the core metric. Pull from <CRM>, form-platform submissions, call-tracking exports |
| Review counts | Reputation delta — public; count live on the listing and date-stamp it, no API needed |
For every NO-ACCESS row: mark the report section "No access yet — requested via the access matrix" and list the ask in the report's "What we need from you" block. Do not silently omit the section — a visible gap creates the urgency that gets access granted.
Step 2 — Pull data (verified sources only)
- Leads: export/read form submissions and
<CRM>records for the month. Tag each lead with a source (form / phone / listing / ads / referral / unknown). "Unknown" is a valid category — report it honestly rather than guessing an attribution. - Cost per lead: only computable when an ad platform is accessible AND spend is known. Otherwise state "organic + direct only this month."
- Reviews: live count + rating per business line, compared against last month's
report (read it from
deliverables/reports/; if none exists, this month sets the baseline — say so). - Work shipped: pull from
<TASK SYSTEM>completed tasks + git log in the client folder. Only list work that is verifiably done — a task marked complete without an artifact you can point at doesn't go in.
Step 3 — Report skeleton (in this order)
- Wins this month — plain language the client's operator understands; lead with their outcome ("11 new leads came through the website"), never with tooling.
- Leads by source — table per business line; total + month-over-month delta once a prior report exists.
- Cost per lead — only with real spend data; otherwise the honest-gap line.
- Reviews & reputation — counts, rating, notable new reviews. Quote real reviews only, verbatim — never compose or "improve" one.
- Work shipped this month — bulleted, dated, deliverable-level.
- Next month's plan — 3–5 items, each tied to a lead-flow or revenue outcome.
- What we need from you — access asks + decisions blocking work.
Step 4 — Tone
Client-facing rules apply (.claude/rules/communication-style.md): "we" never "I", no
emojis, professional but approachable, bold the key numbers. No platform jargon — say
"people who called from your Google listing," not "profile interactions." No pricing or
upsell copy inline — pricing is the founder's conversation, not the report's.
Step 5 — Output
Single self-contained HTML file (inline CSS, client brand colors from
clients/<slug>/brand/), plus a short summary.md beside it:
mkdir -p clients/<slug>/deliverables/reports/$(date +%Y-%m)This is a local deliverable — do NOT deploy it anywhere. If the founder wants a hosted
copy, deploy only with an explicit green-light, via
netlify deploy --prod --site "<YOUR-SITE-ID>" (or your host's equivalent).
Step 6 — Review gate + write-back
- Render and visually read the HTML before handoff — screenshot it, don't trust the source.
- Status is "drafted, awaiting the founder's review" — never "sent" or implied sent. The founder reviews every fact before it reaches the client.
- Write-back: log an activity note on the client's workspace record (date, type:
deliverable, summary + report path) and update the matching
<TASK SYSTEM>task.
Hard gate — regulated topics
If the report (or next month's plan) mentions or implies a regulated topic for a client with a compliance ruleset — promotional financing language, health claims, legal-outcome claims — run regulated-copy-compliance before delivery. Internal metric lines ("2 leads asked about financing") are fine; promotional language is not.
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.

