agentleFS
egdev6egdev6/discord-project-manager/skills/strategy-planner/SKILL.md

strategy-planner

Skill4 starsChanged 5 months agoMITView on GitHub

Produce small planning outputs for network-specific content workflows using approved brand context.

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 13 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to turn approved brand context into a compact planning slice such as a weekly LinkedIn outline, an X queue draft, or a …

    line 9
  2. Distinctive:

    Start from approved brand context when available.

    line 35
  3. Very specific:

    When analytics or trends are provided, consume only sanitized normalized snapshots and trend signals from the shared …

    line 38
  4. Distinctive:

    Put cross-network planning rules in project strategy memory and network-local planning state in the network subtree.

    line 39
  5. Distinctive:

    Keep execution steps for publishing, analytics, and Discord operations out of scope.

    line 40
  6. Distinctive:

    Use only fake/demo values in repository-facing examples.

    line 41
  7. Distinctive:

    Follow ADR 0002 for all namespace references.

    line 42
  8. Distinctive:

    Do not write or revise durable planning memory until a human approves the proposed strategy slice.

    line 99
  9. Distinctive:

    Do not pretend memory writes, Discord routing, or Buffer analytics are already operational.

    line 121
  10. Distinctive:

    Do not consume raw scraped pages, screenshots, native exports, provider payloads, account data, credentials, or private metrics.

    line 122
  11. Distinctive:

    Do not claim live browser/API scraping, analytics ingestion, or trend-provider access until a separate approved implementation exists.

    line 123
  12. Distinctive:

    Do not publish or schedule content from this contract alone.

    line 124
  13. Distinctive:

    Do not put durable cross-network strategy inside runtime Discord namespaces.

    line 125
  14. Distinctive:

    Keep repository examples generic and fake.

    line 126

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Strategy Planner

Use this skill to turn approved brand context into a compact planning slice such as a weekly LinkedIn outline, an X queue draft, or a scoped campaign brief.

This skill proposes plans only. It does not publish, schedule, or claim that Discord, Buffer, or Engram write paths are already fully wired.

Inputs

Required inputs:

  • project_slug
  • network_slug
  • brand_context_summary
  • timeframe
  • goals
  • constraints

Optional inputs:

  • campaign_name
  • recent_ledger_summary
  • normalized_snapshots from social-strategy-analytics-trends-ingestion
  • trend_signals from social-strategy-analytics-trends-ingestion
  • known_assets
  • review_preferences

Behavior

  1. Start from approved brand context when available.
  2. Separate confirmed facts from assumptions.
  3. Produce concise planning structures instead of long prose.
  4. When analytics or trends are provided, consume only sanitized normalized snapshots and trend signals from the shared docs/operations/social-strategy-analytics-trends-ingestion.md contract; join analytics through content_ledger_entry_id, keep unknown metrics as unknown, and preserve trend provenance, timestamp, confidence, and source type in the planning basis.
  5. Put cross-network planning rules in project strategy memory and network-local planning state in the network subtree.
  6. Keep execution steps for publishing, analytics, and Discord operations out of scope.
  7. Use only fake/demo values in repository-facing examples.
  8. Follow ADR 0002 for all namespace references.

Output shape

Return a YAML-like structure similar to this:

project: <project-slug>
network: <network-slug>
timeframe: <timeframe>
strategy_slice:
  goals:
    - <goal>
  assumptions:
    - <assumption>
  sanitized_performance_inputs:
    - content_ledger_entry_id: <ledger id or none>
      network: <network>
      insight: <normalized analytics cue>
  trend_inputs:
    - source_type: <rss|web|search|trend-provider|manual-sanitized-entry>
      observed_at: <timestamp>
      confidence: <0.0-1.0>
      provenance:
        source_kind: <rss-feed|webpage|search-result|trend-report|manual-note>
        retrieved_by: <fake adapter or human-sanitized-entry>
        retrieval_mode: fake-fixture-no-network
        canonical_url: https://example.invalid/<path>
        source_title: <bounded title>
      strategy_signal: <normalized trend cue>
  planned_items:
    - title: <item>
      purpose: <why>
      required_assets:
        - <asset>
  review_checkpoints:
    - <checkpoint>
  out_of_scope:
    - <explicit non-goal>

Memory behavior

Read candidates

  • discord-project-manager/project/<project-slug>/brand
  • discord-project-manager/project/<project-slug>/strategy
  • discord-project-manager/project/<project-slug>/content-ledger
  • discord-project-manager/project/<project-slug>/network/<network-slug>

Write candidates

  • cross-network strategy rules under discord-project-manager/project/<project-slug>/strategy
  • network-local planning context under discord-project-manager/project/<project-slug>/network/<network-slug>

Approval gate

Do not write or revise durable planning memory until a human approves the proposed strategy slice.

Namespace target

Use ADR 0002 exactly:

  • discord-project-manager/project/<project-slug>/strategy
  • discord-project-manager/project/<project-slug>/network/<network-slug>

Canonical ADR examples that this skill may mirror when using fake/demo values:

  • discord-project-manager/project/egdev/strategy
  • discord-project-manager/project/egdev/network/stack-and-flow
  • discord-project-manager/project/egdev/network/youtube
  • discord-project-manager/project/egdev/network/twitch

Promotion to repo artifact

Promote reusable planning rules, review checkpoints, and skill behavior into repo artifacts when they become canonical, reusable, or architecture-relevant. Temporary drafts may remain in Engram until approved.

Safety rules

  • Do not pretend memory writes, Discord routing, or Buffer analytics are already operational.
  • Do not consume raw scraped pages, screenshots, native exports, provider payloads, account data, credentials, or private metrics; require sanitized normalized snapshots instead.
  • Do not claim live browser/API scraping, analytics ingestion, or trend-provider access until a separate approved implementation exists.
  • Do not publish or schedule content from this contract alone.
  • Do not put durable cross-network strategy inside runtime Discord namespaces.
  • Keep repository examples generic and fake.

Demo example (fake)

project: egdev
network: stack-and-flow
timeframe: 2026-W23
strategy_slice:
  goals:
    - test whether short technical clips create demand for longer live sessions
  assumptions:
    - audience prefers implementation trade-offs over motivational framing
  planned_items:
    - title: stack-and-flow demo clip 01
      purpose: tease a longer build breakdown
      required_assets:
        - asset://demo/clip-outline-01
  review_checkpoints:
    - confirm tone still matches project brand context
  out_of_scope:
    - direct publishing

This example is fake/demo data only and must not be treated as a live editorial plan.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.