New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Converge

by agentii-ai in agentii-ai/agentii-investment-intelligence

Append-only gap closure and the cadence engine for research theses.

Apache-2.0Auto-check passedDevelopment

Install Converge

skills CLI
$ npx skills add agentii-ai/agentii-investment-intelligence --skill converge -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agentii-ai/agentii-investment-intelligence converge --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agentii-ai/agentii-investment-intelligence.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/vertical-plugins/scenarios/skills/agentii/converge .claude/skills/converge && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
converge
GitHub stars
207
Token cost
~789 tokens
SKILL.md length
217 words
Files
2 (incl. references)
Skills in repo
79
Repo updated
First seen
Licence
Apache-2.0

At a glance

Append-only gap closure and the cadence engine for research theses.

  • Works in 3 steps: Evaluates current state — artifacts on… → Appends, never rewrites — the only write… → Clean run = byte-identical — no gaps…
  • Tasks that involve Git workflow
  • SKILL.md covers When to run, What it does, Gap types and Invocation, plus 1 more section
  • Calls python3

What it does

Converge is an agent skill from agentii-ai/agentii-investment-intelligence. Append-only gap closure and the cadence engine for research theses. Evaluates artifact CURRENT state (never git history, never task checkboxes) against current pins and wrongif falsifiers, then appends a Convergence section to tasks.md re-proposing the gaps. A clean run leaves tasks.md byte-identical. Deterministic gaps (stale, invalidated) are uncapped; judgment-class gaps are capped per spec 046 Q40.

Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/modes.md`).

It sits in Development, covering Git workflow. The repository describes itself as: Claude-type skills for institutional equity research — 25 AI agent skills with SEC filings, XBRL financials, earnings calendars, DCF/comps/LBO models, and PPT generation. Powered… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Git workflow

Example prompts

  • “/converge”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Evaluates current state — artifacts on disk, pins in frontmatter, wrong_if
  2. Appends, never rewrites — the only write is a ## Phase N: Convergence
  3. Clean run = byte-identical — no gaps means no empty section header.

What it can do on your machine

Read from SKILL.md and the folder at commit 86980e1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Converge loads about 789 tokens when it runs, and up to ~963 if it reads all its reference files. Until then it costs about 104 tokens; SKILL.md has 217 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~104
When it runs · the whole SKILL.md, loaded when a task matches
~789
With references · SKILL.md plus every file in references/, read only if the agent opens them
~963

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from agentii-ai/agentii-investment-intelligence at commit 86980e1, republished under its Apache-2.0 licence (© agentii-ai). 217 words, ~789 tokens.

Download SKILL.mdSave it as .claude/skills/converge/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
converge
description
Append-only gap closure and the cadence engine for research theses. Evaluates artifact CURRENT state (never git history, never task checkboxes) against current pins and wrong_if falsifiers, then appends a Convergence section to tasks.md re-proposing the gaps. A clean run leaves tasks.md byte-identical. Deterministic gaps (stale, invalidated) are uncapped; judgment-class gaps are capped per spec 046 Q40.
role
kit
market_data_stage
none
retrieval_scope
structured_only

agentii.converge

Append-only gap closure — the cadence engine of the research orchestration system (spec 046 Q26).

When to run

  • After every agentii.implement batch (the system detects its own staleness).
  • On any cadence cycle (quarterly re-visits, post-earnings, post-constitution-bump).
  • Before any IC review (the conflict list must be current).
  • When the cross-stock synthesis tasks complete, close the loop with the report workflow — see skills/agentii/synthesize/SKILL.md (pack → author content.html → assemble). An html_stale finding below means that workflow must re-run.

What it does

  1. Evaluates current state — artifacts on disk, pins in frontmatter, wrong_if falsifiers in thesis.md. It never reads git history and never trusts [x] checkboxes (Q26 A+: the ledger may lie; the correction is deterministic and has a bounded expiry — the next converge).
  2. Appends, never rewrites — the only write is a ## Phase N: Convergence section at the end of tasks.md, with src: refs and content-derived finding IDs. Existing lines, including previous Convergence sections, are untouched.
  3. Clean run = byte-identical — no gaps means no empty section header.

Gap types

TypeClassCap
stale (pins older than current)deterministicuncapped
invalidated (wrong_if metric+threshold triggered)deterministicuncapped
missing / partial / contradicts / unrequestedjudgmentQ40 cap (≈50)

Invocation

bash
# Resolve the kit root first — contracts/kit-root.md. The kit's scripts do NOT ship
# with the skills, so never assume the CWD is the checkout.
KIT=""
for c in "${AGENTII_KIT_ROOT:-}" \
         "$(cat "$HOME/.claude/skills/agentii/.kit-root" 2>/dev/null)" \
         "${CLAUDE_PLUGIN_ROOT:-}"; do
  [ -n "$c" ] && [ -f "$c/scripts/agentii_cmd.py" ] && { KIT="$c"; break; }
done
if [ -z "$KIT" ]; then d="$PWD"; while [ "$d" != "/" ]; do
  [ -f "$d/scripts/agentii_cmd.py" ] && { KIT="$d"; break; }; d="$(dirname "$d")"; done; fi
[ -n "$KIT" ] || { echo "agentii kit not found — see contracts/kit-root.md" >&2; exit 1; }

python3 "$KIT/scripts/converge.py" --thesis theses/001-ai-semiconductors \
  --pins '{"assumption_pin": 1, "corpus_version": "2026-08", "as_of": "2026-09-08", "constitution_pin": "0.1.0", "skill_pin": "recent-quarter:abc"}'

Hard rules (Q26)

  • Never modify spec.md or plan.md.
  • Never rewrite, renumber, reorder, or delete any existing task.
  • Finding IDs are content-derived (hash(entity+metric+period+gap_type)) — an unchanged re-run appends nothing.

© agentii-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/vertical-plugins/scenarios/skills/agentii/converge of agentii-ai/agentii-investment-intelligence.

  • SKILL.md
  • references/modes.md

Open the folder on GitHubat commit 86980e1

Compare with similar skills

Converge next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Converge compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Converge this skillagentii-ai/agentii-investment-intelligence207—~789Automated safety check: PassApache-2.0
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Code Design Rationale Investigatorcursor/plugins11k9 repos~2.6kAutomated safety check: PassNone
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Migrate Internal Package into GhostTryGhost/Ghost56k—~3.8kAutomated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0

Similar skills

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Code Design Rationale Investigator

    cursor/plugins

    Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    11k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed

  • Contributor-First PR Merge

    HKUDS/OpenHarness

    Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed

  • Migrate Internal Package into Ghost

    TryGhost/Ghost

    Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.

    56k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed

  • Create Pull Request

    cline/cline

    Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

  • Contextual Commit Messages

    yamadashy/repomix

    Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.

    29k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed

More from agentii-ai/agentii-investment-intelligence

All 79 skills in this repo

  • Challenge

    agentii-ai/agentii-investment-intelligence

    Adversarial verification of research theses — cross-run/cross-thesis contradiction via the entity index, pre-mortem (Klarman/Kahneman: assume the loss already happened, reverse the path), inversion…

    207 GitHub stars~735 tokensUpdated 11 days ago
    Auto-check passed

  • Chart Patterns

    agentii-ai/agentii-investment-intelligence

    Chart pattern recognition, price action patterns, candlestick signal bars, pullback bar counting H1/H2/H3/H4, trend channels, micro channels, trading ranges, breakouts, major trend reversals 5-step…

    207 GitHub stars~2k tokensUpdated 11 days ago
    Auto-check passed

  • Clarify

    agentii-ai/agentii-investment-intelligence

    The research-domain clarification skill — find underspecified items in a thesis spec.md (prose wrongif, universe rows without rationale, missing budget/expiry/pins, ambiguous pillars), ask the human…

    207 GitHub stars~839 tokensUpdated 11 days ago
    Auto-check passed

  • Constitution

    agentii-ai/agentii-investment-intelligence

    Scaffold and amend the L1 Investment Constitution — [ALLCAPS] placeholder bootstrap, SemVer bump rules, Sync Impact Report, MINOR/MAJOR re-examination dispatch after the gate-5 budget confirm.

    207 GitHub stars~596 tokensUpdated 11 days ago
    Auto-check passed

  • Implement

    agentii-ai/agentii-investment-intelligence

    Execute research tasks — checklist soft gate, phase dispatch with explicit thesisdir, budget enforcement (halt + approval card on overrun), skillpin recording (versionhash content-hashed per skill…

    207 GitHub stars~583 tokensUpdated 11 days ago
    Auto-check passed

  • Market Share Tracking

    agentii-ai/agentii-investment-intelligence

    Weekly product-level commercial tracking — TRx/NRx with current/4-wk/12-wk share and YoY, launch curves overlaid with same-class analogs plus a consensus-implied trajectory, LOE/biosimilar erosion…

    207 GitHub stars~1.9k tokensUpdated 11 days ago
    Auto-check passed

Categories

Questions about Converge

What does Converge do?

Append-only gap closure and the cadence engine for research theses. Converge is an agent skill from agentii-ai/agentii-investment-intelligence. Append-only gap closure and the cadence engine for research theses.

When should I use Converge?

Converge fits situations like: tasks that involve Git workflow.

How do I install Converge in Claude Code?

Run `npx skills add agentii-ai/agentii-investment-intelligence --skill converge -a claude-code`. Or copy the skill folder (plugins/vertical-plugins/scenarios/skills/agentii/converge in agentii-ai/agentii-investment-intelligence) into .claude/skills/converge in your project. Claude Code loads it when a task matches its description.

How do I install Converge in Codex?

Run `npx skills add agentii-ai/agentii-investment-intelligence --skill converge -a codex`. Or copy the skill folder (plugins/vertical-plugins/scenarios/skills/agentii/converge in agentii-ai/agentii-investment-intelligence) into .agents/skills/converge in your project. Codex loads it when a task matches its description.

Can I use Converge in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentii-ai/agentii-investment-intelligence --skill converge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/converge, .gemini/skills/converge, .github/skills/converge and .opencode/skills/converge in your project.

What does Converge need to run?

Going by SKILL.md and its folder, Converge needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Converge access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Converge safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Converge use?

Converge is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Converge use?

About 789 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 174 tokens, read only when the agent opens those files.

What are the alternatives to Converge?

Skills that share tags, products or a category with Converge: Finishing a Development Branch (obra/superpowers, 297k stars), Code Design Rationale Investigator (cursor/plugins, 11k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Migrate Internal Package into Ghost (TryGhost/Ghost, 56k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Converge?

agentii-ai (a GitHub user) maintains it in agentii-ai/agentii-investment-intelligence, which has 207 GitHub stars. The repository holds 79 skills in this directory. The repository was last updated on September 29, 2026.

Source: agentii-ai/agentii-investment-intelligence on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.