SkillsAdd

Source

doodledood/manifest-dev

34 skills · 267 combined installs

Skills from this source

#
Skill
Source
8W Activity
Installs
1
define
doodledood/manifest-dev
23
2
do Manifest executor. Works through Deliverables verifying every Acceptance Criterion and Global Invariant. Use when exe…
doodledood/manifest-dev
23
3
figure-out Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached.…
doodledood/manifest-dev
10
4
auto End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want t…
doodledood/manifest-dev
8
5
prompt-engineering Create, update, review, or discuss an LLM prompt — a system prompt, a skill, or an agent. Use when writing or improvi…
doodledood/manifest-dev
8
6
review-code Review a change along one specific quality dimension — bugs, design, simplicity, maintainability, testability, test q…
doodledood/manifest-dev
8
7
review-prompt Review LLM prompts against the prompt-engineering skill's principles — leading with where each line came from — and r…
doodledood/manifest-dev
8
8
babysit-pr Author-side PR lifecycle babysitter and companion to review-pr. Use when the user wants to tend an existing GitHub PR…
doodledood/manifest-dev
7
9
check-pr Read-only inspection of a single GitHub PR lifecycle — checks CI, review threads, description sync, and mergeability,…
doodledood/manifest-dev
7
10
design Design and build user-visible artifacts — pages, dashboards, tools, documents, reports, decks, infographics, posters,…
doodledood/manifest-dev
7
11
done Completion marker for the /do workflow. Outputs a plain-prose summary of what was built. Called by /do after every Ac…
doodledood/manifest-dev
7
12
eli5 Explain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a dead-simple picture explai…
doodledood/manifest-dev
7
13
escalate Structured escalation when /do hits an unrecoverable blocker. Surfaces what was tried, why it failed, and what the us…
doodledood/manifest-dev
7
14
figure-out-team Drive a multi-party deliberation in a Slack channel or thread. The agent is an involved orchestrator — presses rigoro…
doodledood/manifest-dev
7
15
handoff Produce a self-contained context payload that lets a fresh agent continue without re-deriving what this session estab…
doodledood/manifest-dev
7
16
init-context Set a project up with the surfaces manifest-dev works from — a North Star, a glossary, ADR conventions, and the conte…
doodledood/manifest-dev
7
17
just-auto Goal-based autonomous chain: figures out the task, encodes a Manifest, and pursues it end-to-end with full autonomy a…
doodledood/manifest-dev
7
18
just-define Goal-based Manifest builder. Encodes shared understanding into a verifiable Manifest — Deliverables, Acceptance Crite…
doodledood/manifest-dev
7
19
just-do Goal-based Manifest executor. Reads a Manifest and pursues it with full autonomy: reach a state where every Acceptanc…
doodledood/manifest-dev
7
20
just-figure-out Goal-based investigation partner. Presses a topic until understanding is shared and names a read — conclusion, confid…
doodledood/manifest-dev
7
21
next-ticket Read the project's Ticket store, choose the single best Ticket for the human-plus-AI session to work on now, claim it…
doodledood/manifest-dev
7
22
review-design Review a user-visible artifact against design standards — a page, dashboard, tool, document, report, deck, infographi…
doodledood/manifest-dev
7
23
review-pr Autonomous PR review that posts high-signal, human-voiced comments under your account. Use when reviewing someone els…
doodledood/manifest-dev
7
24
review-writing Review any prose against this project's writing standards — a README, a spec, a design doc, a blog post, marketing co…
doodledood/manifest-dev
7
25
run-ticket Run one exact Ticket through recovery, autonomous work, and its required landing, then write DONE or ESCALATED eviden…
doodledood/manifest-dev
7
26
sweep-tickets Recover or start one unattended Ticket from a configured shared Ticket Store, then stop. Use from a scheduled agent t…
doodledood/manifest-dev
7
27
teach-me Teach the learner to deeply understand a body of work — the current session's changes, a PR, an ADR, or any topic the…
doodledood/manifest-dev
7
28
ticket-up Author self-sufficient Tickets in the project's store from a finished Manifest, a direct work request, an open questi…
doodledood/manifest-dev
7
29
walk-pr Walk through a PR or large diff together — your own or someone else's — one sub-changeset at a time and one review to…
doodledood/manifest-dev
7
30
poll-slack Narrate new Slack messages in a channel or thread since a cursor. Returns a natural-language story of what was said, …
doodledood/manifest-dev
6
31
review-pr-holistic Called by review-pr after its reviewer fleet and judgment pass return: consolidates their findings against the PR's h…
doodledood/manifest-dev
6
32
review-pr-judgment Called by review-pr in both of its modes: the whole-PR premise check that asks whether a change earns its keep agains…
doodledood/manifest-dev
6
33
review-pr-thread-verify Called by review-pr for each unresolved review thread it authored: judges from the thread, the author's replies, and …
doodledood/manifest-dev
6
34
auto-optimize-prompt Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities,…
doodledood/manifest-dev
1