Index of every page on this site: llms.txt
All skills
deanpeters avatar

/pricing-packaging-tracker

@476ae12
Run it yourself

Track competitor pricing and packaging as a diffable time series. Use when monitoring tiers, gates, limits, and price moves on a monthly or quarterly cadence.

Use this Skill: https://skilld.dev/gh/deanpeters/product-manager-skills/pricing-packaging-tracker

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈46 tokens for metadata: the name and description. ≈2.1k when used: this file. ≈3.3k more on demand in 3 files.

Description uses 2.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈186 characters, or 2.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Pricing & Packaging Tracker

Purpose

Track competitor pricing and packaging as a diffable time series, not a screenshot: capture (or diff) → structure changes → price changes → signals → next-step options. The stable capture schema is the point — run N diffs against run N-1, so the report is what moved, with evidence. And the skill watches structure as closely as numbers, because packaging changes (gates, limits, tier restructures) usually signal strategy earlier than price changes do: a tier that disappears telegraphs a move upmarket months before the price list admits it.

Input

Works best with: the competitor set to track (or the snapshot they came from), and the prior pricing capture if one exists — that's what turns this run into a delta report. Also useful: your own pricing context, if the comparison should include you.

Input supplied inline with the invocation — text after the skill name, a pasted context dump, or an appended ARGUMENTS: line — counts as answers already given. Use it against the question budget; don't re-ask.

Arriving empty-handed? That works too. With no prior capture the skill runs baseline mode: full capture per competitor, and the delta value starts next run. With no competitor list, it asks — that's one of its two budget questions.

Example invocation: Pricing tracker on [Competitor A], [Competitor B], [Competitor C] — prior capture from April pasted below.

Key Concepts

  • Governing protocol: honors the autonomous-investigation contract — question budget of 2, Fact/Inference/Assumption labels, Just Enough Mode, stable schema, 4-option Final Step. Discipline: SIGINT (pricing pages, site diffs) with FININT corroboration — see intelligence-collection-disciplines.
  • Time series, not screenshot. A single capture is trivia; the sequence is intelligence. The schema never drifts between runs, because diffability is the entire value.
  • Structure over numbers. Record tiers, billing units, feature gates, usage limits, free-tier boundaries, and enterprise-floor signals — not just prices. The gate moves first; the price follows.
  • "Contact sales" is data, honestly labeled. Where pricing is opaque, track what is public (editions, gates, published floors) and mark the rest. Infer only with labels; never invent prices, tiers, limits, discounts, or negotiated figures.
  • When NOT to use: you need pricing strategy advice → finance-based-pricing-advisor (this tracks the market; it doesn't set your price); pricing is fully opaque across the whole set → expect thin results, and consider voice-of-customer-miner or win/loss evidence instead.

Application

  1. Determine mode. Prior capture provided → delta mode (report changes only). None → baseline mode (full capture, then stop).
  2. Credit inline context, then ask only the unanswered questions (max 2):
    1. Which competitors' pricing should I track?
    2. Prior capture to diff against, or is this the baseline?
  3. Capture from live pricing pages — plan-comparison pages, published rate cards, credible pricing-change coverage — with URL and as-of date per competitor.
  4. Emit the schema below exactly — diffability is the point.

Output schema (do not reorder)

# Pricing Capture / Delta Report

## 1. Run Header
**Competitor set:** | **Prior capture date:** [or "baseline run"] | **This run date:**

## 2. Pricing Capture (per competitor)
### [Competitor] — [pricing page URL, as-of date]
- **Tiers:** [name: price / unit / billing terms, one bullet each]
- **Key gates:** [which capabilities gate which tier, 2-4 bullets]
- **Usage limits:** [the limits that matter, 1-2 bullets]
- **Free tier / trial:** [boundary, 1 bullet]
- **Enterprise signals:** [published floors, "contact sales" scope]

(Baseline mode: full capture per competitor. Delta mode: this section
only for competitors with changes.)

## 3. Changes Since Last Capture (Delta Mode)
### [Competitor] — [4 to 8 word change summary]
- **Then / Now:** [old -> new, labeled Fact]
- **Evidence:** [URL, date]
- **Reading:** [Inference — repositioning, monetization push, response to whom?]

If nothing changed: "No pricing or packaging changes this cycle."

## 4. Signals
- [Cross-competitor patterns: direction of the market's pricing, labeled]
- [Implications for your pricing or battle cards: 2-3 bullets]

### Assumptions to Validate
- [Assumption 1] / [Assumption 2] / [Assumption 3]

A copy/paste fill-in version of this schema, with quality checks, lives in template.md.

Final Step (offer exactly 4 options)

  1. Update battle card pricing sections from these changes (battle-card-builder)
  2. Deep-dive one competitor's packaging logic
  3. Compare your pricing against this capture
  4. Set the cadence and watchlist for the next run

Accept 1, 2, 3, 4, 1 and 2, Verbose Mode, or a custom path.

Examples

A delta entry reading structure, not just price (fictional):

[Competitor B] — API access moved from Pro to new Scale tier

  • Then / Now: API access included in Pro ($79/seat) → gated behind new "Scale" tier ($149/seat, 10-seat minimum) — Fact
  • Evidence: [pricing page vs. archived capture, URL, dates]
  • Reading: the price didn't change; the gate did. Developer-led accounts are being pushed into a sales conversation — Inference: monetization push on their fastest-growing usage pattern, and a window for us with API-first buyers while their community absorbs it.

The cross-competitor signal: three of four tracked competitors added usage-based add-ons this quarter while holding seat prices flat — Inference: the market is testing consumption pricing without headline price increases. Your pricing debate is no longer hypothetical; the Signals section names the evidence.

See examples/sample.md for a complete worked delta run (fictional FSM-software market) where both material moves are structural — a new tier and a relocated gate — and no headline price changed at all. examples/sample-industrial.md shows the fully opaque case: zero published prices, and structure as the only public signal.

Common Pitfalls

  • Screenshot thinking. Capturing once and calling it competitive pricing intel. The value compounds only on a cadence — baseline, then diff, forever.
  • Number fixation. Reporting only price changes while a tier quietly gained a 5-seat minimum. Structure is the leading indicator; watch the gates.
  • Inventing the opaque. Filling "contact sales" cells with plausible figures. Publish the honest boundary and label any inference — a battle card built on invented enterprise pricing detonates in a live deal.
  • Schema improvisation. Reordering or "improving" the capture format between runs breaks every future diff. The schema is a contract with your own future runs.
  • Tracking without a consumer. If no battle card, pricing review, or watch report consumes the output, the cadence dies quietly. Wire the Final Step's first option into a real artifact.

References

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning4mo3 checks · Risk SAFE
  • Gen Agent Trust Hub4mo

    This skill tracks competitor pricing and packaging by analyzing public web pages. It is functionally safe, with no detected malicious code, exfiltration patterns, or obfuscation. It includes a minor risk of indirect prompt injection inherent to processing external website content.

  • Socket4mo

    No alerts

  • Snyk4mo

    Risk: MEDIUM · 1 issue

Signed by skilld at 476ae12. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 4 months ago
argument-hint
[competitor set, and prior capture if one exists]
type
workflow
theme
market-intelligence
Other metadata
intent
Capture competitor public pricing pages into a stable schema, diff against the prior capture, and report tier changes, price moves, feature-gate shifts, and packaging restructures with URLs and dates — because packaging changes signal strategy earlier than price changes do.
best_for
[
  "Keeping battle-card pricing sections current without manual screenshot archaeology",
  "Catching packaging restructures — the earliest public signal of a strategy shift",
  "Building the pricing time series that grounds your own pricing decisions"
]
scenarios
[
  "Baseline the pricing pages of our four main competitors, then track monthly",
  "Did anyone in our space change pricing or packaging this quarter?"
]
estimated_time
15-30 min per run

README badge

README badge for deanpeters/product-manager-skills/pricing-packaging-tracker